<script src="https://bibbase.org/service/mendeley/079852a8-52df-3ac8-a41c-8bebd97d6b2b?jsonp=1"></script>
<?php
$contents = file_get_contents("https://bibbase.org/service/mendeley/079852a8-52df-3ac8-a41c-8bebd97d6b2b");
print_r($contents);
?>
<iframe src="https://bibbase.org/service/mendeley/079852a8-52df-3ac8-a41c-8bebd97d6b2b"></iframe>
For more details see the documention.
To the site owner:
Action required! Mendeley is changing its API. In order to keep using Mendeley with BibBase past April 14th, you need to:
@article{
title = {Dual Interactive Graph Convolutional Networks for Hyperspectral Image Classification},
type = {article},
year = {2022},
pages = {1-14},
volume = {60},
id = {8c894b5d-a5bc-3c26-8417-981186c480c7},
created = {2021-06-12T06:28:35.731Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:31.661Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {9426925},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Wan, Sheng and Pan, Shirui and Zhong, Ping and Chang, Xiaojun and Yang, Jian and Gong, Chen},
doi = {10.1109/TGRS.2021.3075223},
journal = {IEEE Transactions on Geoscience and Remote Sensing (TGRS)}
}
@article{
title = {A Survey on Knowledge Graphs: Representation, Acquisition, and Applications},
type = {article},
year = {2022},
pages = {494-514},
volume = {33},
id = {ad69cfd4-d6bb-3718-9ddb-eef7688d709b},
created = {2021-06-12T06:28:36.811Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:33.984Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {9416312},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Ji, Shaoxiong and Pan, Shirui and Cambria, Erik and Marttinen, Pekka and Yu, Philip S},
doi = {10.1109/TNNLS.2021.3070843},
journal = {IEEE Transactions on Neural Networks and Learning Systems (TNNLS)},
number = {2}
}
@article{
title = {One-shot Learning-based Animal Video Segmentation},
type = {article},
year = {2022},
pages = {3799-3807},
volume = {18},
id = {34de762f-bbf8-32e5-873c-073eeeb1d0ba},
created = {2021-10-03T12:05:36.647Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:30.871Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {tii-21-xue},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Xue, Tengfei and Qiao, Yongliang and Kong, He and Su, Daobilige and Pan, Shirui and Rafique, Khalid and Sukkarieh, Salah},
doi = {10.1109/TII.2021.3117020},
journal = {IEEE Transactions on Industrial Informatics (TII)},
number = {6}
}
@inproceedings{
title = {Predicting Human Mobility via Graph Convolutional Dual-attentive Networks},
type = {inproceedings},
year = {2022},
pages = {192–200 (CORE Ranked A*)},
publisher = {ACM},
id = {92d151ca-2f10-38a7-8648-830c6e669ebb},
created = {2022-02-17T12:32:04.129Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:28.385Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {wsdm22dang},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
bibtype = {inproceedings},
author = {Dang, Weizhen and Wang, Haibo and Pan, Shirui and Zhang, Pei and Zhou, Chuan and Chen, Xin and Wang, Jilong},
doi = {https://doi.org/10.1145/3488560.3498400},
booktitle = {International Conference on Web Search and Data Mining (WSDM)}
}
@inproceedings{
title = {Dual Space Graph Contrastive Learning},
type = {inproceedings},
year = {2022},
publisher = {ACM},
id = {531fa3b0-5f6f-3063-a778-90737b016d9c},
created = {2022-02-17T12:32:04.139Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:34.921Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {www22yang},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
bibtype = {inproceedings},
author = {Yang, Haoran and Chen, Hongxu and Pan, Shirui and Li, Lin and Yu, Philip S and Xu, Guandong},
booktitle = {The Web Conference (WWW)}
}
@inproceedings{
title = {Exploring Relational Semantics for Inductive Knowledge Graph Completion},
type = {inproceedings},
year = {2022},
publisher = {AAAI Press},
id = {1206e4a1-6487-380a-b7cb-6181186cabdf},
created = {2022-02-17T12:32:04.785Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:33.220Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {aaai22wang},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
bibtype = {inproceedings},
author = {Wang, Changjian and Zhou, Xiaofei and Pan, Shirui and Dong, Linhua and Song, Zeliang and Sha, Ying},
booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)}
}
@inproceedings{
title = {Towards Unsupervised Deep Graph Structure Learning},
type = {inproceedings},
year = {2022},
publisher = {ACM},
id = {64e1bd10-c058-3230-b101-8baec7c35ad4},
created = {2022-02-17T12:32:04.817Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:32.435Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {www22liu},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
bibtype = {inproceedings},
author = {Liu, Yixin and Zheng, Yu and Zhang, Daokun and Chen, Hongxu and Peng, Hao and Pan, Shirui},
booktitle = {The Web Conference (WWW)}
}
@article{
title = {Reinforced, Incremental and Cross-lingual Event Detection From Social Messages},
type = {article},
year = {2022},
pages = {1},
id = {5e7d7753-7610-37a3-95e7-713221a7229b},
created = {2022-02-17T12:39:52.498Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:30.087Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {tpami22peng},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Peng, Hao and Zhang, Ruitong and Li, Shaoning and Cao, Yuwei and Pan, Shirui and Yu, Philip S},
doi = {10.1109/TPAMI.2022.3144993},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)}
}
@article{
title = {Attraction and Repulsion: Unsupervised Domain Adaptive Graph Contrastive Learning Network},
type = {article},
year = {2022},
pages = {1},
id = {5d45afdf-d579-32a4-9200-fe74d818ae69},
created = {2022-02-17T12:39:52.498Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:29.181Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {tetci22wu},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Wu, Man and Pan, Shirui and Zhu, Xingquan},
journal = {IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI)}
}
@inproceedings{
title = {BaLeNAS: Differentiable Architecture Search via Bayesian Learning Rule},
type = {inproceedings},
year = {2022},
id = {7231be03-37fe-3348-a757-9dcd07add323},
created = {2022-04-11T02:13:23.584Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-11T02:14:57.706Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {cvpr_zhang_2022},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d},
private_publication = {false},
bibtype = {inproceedings},
author = {Zhang, Miao and Pan, Shirui and Chang, Xiaojun and Su, Steven and Hu, Jilin and Haffari, Reza and Yang, Bin},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR-22, New Orleans, Louisiana, US, Jun 19-24, 2022 (accepted on 03/03/2022) (CORE Ranked A*)}
}
@inproceedings{
title = {Fire Burns, Swords Cut: Commonsense Inductive Bias for Exploration in Text-based Games},
type = {inproceedings},
year = {2022},
id = {125fb2ee-5bc9-3d21-ad1c-e03bcf6a22ff},
created = {2022-04-11T02:13:23.668Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-11T02:14:57.640Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {acl_ryu_2022},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d},
private_publication = {false},
bibtype = {inproceedings},
author = {Ryu, Dongwon and Shareghi, Ehsan and Fang, Meng and Xu, Yunqiu and Pan, Shirui and Haffari, Reza},
booktitle = {60th Annual Meeting of the Association for Computational Linguistics (ACL-2022), Dublin, Ireland, May 22-27, 2022 (accepted on 24/02/2022) (CORE Ranked A*)}
}
@inproceedings{
title = {Cross-modal Clinical Graph Transformer For Ophthalmic Report Generation},
type = {inproceedings},
year = {2022},
id = {12df74b6-866a-3d24-ba7e-3f06a96a343f},
created = {2022-04-11T02:13:24.257Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-11T02:14:58.019Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {cvpr_li_2022},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d},
private_publication = {false},
bibtype = {inproceedings},
author = {Li, Mingjie and Cai, Wenjia and Verspoor, Karin and Pan, Shirui and Li, Xiaodan and Chang, Xiaojun},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR-22, New Orleans, Louisiana, US, Jun 19-24, 2022 (accepted on 03/03/2022) (CORE Ranked A*)}
}
@inproceedings{
title = {A Probabilistic Graphical Model Based on Neural-symbolic Reasoning for Visual Relationship Detection},
type = {inproceedings},
year = {2022},
id = {83c047e1-dce5-3763-b887-11b90218ea62},
created = {2022-04-11T02:13:24.384Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-11T02:14:58.809Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {cvpr_yu_2022},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d},
private_publication = {false},
bibtype = {inproceedings},
author = {Yu, Dongran and Yang, Bo and Wei, Qianhao and Li, Anchen and Pan, Shirui},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR-22, New Orleans, Louisiana, US, Jun 19-24, 2022 (accepted on 03/03/2022) (CORE Ranked A*)}
}
@inproceedings{
title = {Towards Spatio-Temporal Aware Traffic Time Series Forecasting},
type = {inproceedings},
year = {2022},
id = {2fd0b2a4-3b06-33d1-9b05-578b90967e9f},
created = {2022-04-11T02:13:24.626Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-11T02:14:58.617Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {icde_razvan_2022},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d},
private_publication = {false},
bibtype = {inproceedings},
author = {Cirstea, Razvan and Yang, Bin and Guo, Chenjuan and Kieu, Tung and Pan, Shirui},
booktitle = {IEEE International Conference on Data Engineering (ICDE-22), (Virtual) Kuala Lumpur, Malaysia, May 9-12, 2022 (accepted on 14/01/2022) (CORE Ranked A*)}
}
@article{
title = {Predicting Best-Selling New Products in a Major Promotion Campaign Through Graph Convolutional Networks},
type = {article},
year = {2022},
pages = {1-14},
id = {e11a36ac-36de-35a0-996b-d9707fe27b4a},
created = {2022-04-11T02:13:24.641Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-11T02:13:25.704Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {tnnls_li_2022},
source_type = {article},
folder_uuids = {a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Li, Chaojie and Jiang, Wensen and Yang, Yin and Pan, Shirui and Guo, Lijie and Huang, Gang},
doi = {10.1109/TNNLS.2022.3155690 (Impact Factor: 10.451; JCR Ranked Q1)},
journal = {IEEE Transactions on Neural Networks and Learning Systems (TNNLS)}
}
@inproceedings{
title = {Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning},
type = {inproceedings},
year = {2021},
pages = {10049-10057 (CORE Ranked A*)},
publisher = {AAAI Press},
id = {6ee01df7-3eb2-3c3b-bccb-8db58ccfebd1},
created = {2021-06-12T06:28:35.030Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:35.712Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {DBLP:conf/aaai/WanPY021},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
bibtype = {inproceedings},
author = {Wan, Sheng and Pan, Shirui and Yang, Jian and Gong, Chen},
booktitle = {Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021}
}
@article{
title = {One-Shot Neural Architecture Search: Maximising Diversity to Overcome Catastrophic Forgetting},
type = {article},
year = {2021},
pages = {2921-2935},
volume = {43},
id = {06e272a0-e764-3e04-a2f7-efa3c38a6a18},
created = {2021-06-12T06:28:35.037Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:36.476Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {9247292},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Zhang, Miao and Li, Huiqi and Pan, Shirui and Chang, Xiaojun and Zhou, Chuan and Ge, Zongyuan and W. Su, Steven},
doi = {10.1109/TPAMI.2020.3035351},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
number = {9}
}
@article{
title = {Suicidal Ideation Detection: A Review of Machine Learning Methods and Applications},
type = {article},
year = {2021},
pages = {214-226},
volume = {8},
id = {c026b621-5bc7-3e15-92f6-cf8a83ac2cc6},
created = {2021-06-12T06:28:35.720Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:49.615Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {9199553},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Ji, Shaoxiong and Pan, Shirui and Li, Xue and Cambria, Erik and Long, Guodong and Huang, Zi},
doi = {10.1109/TCSS.2020.3021467},
journal = {IEEE Transactions on Computational Social Systems (TCSS)},
number = {1}
}
@article{
title = {Identify Topic Relations in Scientific Literature Using Topic Modeling},
type = {article},
year = {2021},
pages = {1232-1244},
volume = {68},
id = {8d245b8c-6f70-39f6-85dd-bbab1da47be7},
created = {2021-06-12T06:28:36.115Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:38.898Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {8682076},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Chen, Hongshu and Wang, Ximeng and Pan, Shirui and Xiong, Fei},
doi = {10.1109/TEM.2019.2903115},
journal = {IEEE Transactions on Engineering Management (TEM)},
number = {5}
}
@article{
title = {Convolutional Neural Networks based Lung Nodule Classification: A Surrogate-Assisted Evolutionary Algorithm for Hyperparameter Optimization},
type = {article},
year = {2021},
pages = {869-882},
volume = {25},
id = {09f0fc5e-ded4-33a0-8f7a-822ccabe6b50},
created = {2021-06-12T06:28:36.118Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:47.766Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {9359655},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Zhang, Miao and Li, Huiqi and Pan, Shirui and Lyu, Juan and Ling, Steve and Su, Steven},
doi = {10.1109/TEVC.2021.3060833},
journal = {IEEE Transactions on Evolutionary Computation (TEvC)},
number = {5}
}
@article{
title = {Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning},
type = {article},
year = {2021},
pages = {1-15},
id = {a1deec42-29b2-3797-9019-812a6b67ae1a},
created = {2021-06-12T06:28:36.398Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:40.489Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {9395172},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Liu, Yixin and Li, Zhao and Pan, Shirui and Gong, Chen and Zhou, Chuan and Karypis, George},
doi = {10.1109/TNNLS.2021.3068344},
journal = {IEEE Transactions on Neural Networks and Learning Systems (TNNLS)}
}
@article{
title = {Temporal Network Embedding for Link Prediction via VAE Joint Attention Mechanism},
type = {article},
year = {2021},
pages = {1-14},
id = {ecc44ae3-966e-349f-8f40-e6bce20f81f1},
created = {2021-06-12T06:28:36.419Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:42.361Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {9449483},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Jiao, Pengfei and Guo, Xuan and Jing, Xin and He, Dongxiao and Wu, Huaming and Pan, Shirui and Gong, Maoguo and Wang, Wenjun},
doi = {10.1109/TNNLS.2021.3084957},
journal = {IEEE Transactions on Neural Networks and Learning Systems (TNNLS)}
}
@article{
title = {A Comprehensive Survey on Graph Neural Networks},
type = {article},
year = {2021},
pages = {4-24},
volume = {32},
id = {976789ce-40dd-3b54-8373-6a5da82153a7},
created = {2021-06-12T06:28:36.831Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:41.928Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {9046288},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Wu, Zonghan and Pan, Shirui and Chen, Fengwen and Long, Guodong and Zhang, Chengqi and Yu, Philip S},
doi = {10.1109/TNNLS.2020.2978386},
journal = {IEEE Transactions on Neural Networks and Learning Systems (TNNLS)},
number = {1}
}
@article{
title = {Influence Spread in Geo-Social Networks: A Multiobjective Optimization Perspective},
type = {article},
year = {2021},
pages = {2663-2675},
volume = {51},
id = {192afe9a-57a2-3a61-a9d2-0f0c757cc5ba},
created = {2021-06-12T06:28:36.846Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:51.215Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {8681274},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Wang, Liang and Yu, Zhiwen and Xiong, Fei and Yang, Dingqi and Pan, Shirui and Yan, Zheng},
doi = {10.1109/TCYB.2019.2906078},
journal = {IEEE Transactions on Cybernetics (TCYB)},
number = {5}
}
@article{
title = {Graph Learning: A Survey},
type = {article},
year = {2021},
pages = {109-127},
volume = {2},
id = {39db748c-2b90-338c-a306-dff91ef69857},
created = {2021-06-12T06:28:37.147Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:45.003Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {9416834},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Xia, Feng and Sun, Ke and Yu, Shuo and Aziz, Abdul and Wan, Liangtian and Pan, Shirui and Liu, Huan},
doi = {10.1109/TAI.2021.3076021},
journal = {IEEE Transactions on Artificial Intelligence (TAI)},
number = {2}
}
@article{
title = {Hyperspectral Image Classification With Context-Aware Dynamic Graph Convolutional Network},
type = {article},
year = {2021},
pages = {597-612},
volume = {59},
id = {755d225c-af6d-35ab-b304-78b68ad7f31f},
created = {2021-06-12T06:28:37.451Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:39.729Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {9099071},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Wan, Sheng and Gong, Chen and Zhong, Ping and Pan, Shirui and Li, Guangyu and Yang, Jian},
doi = {10.1109/TGRS.2020.2994205},
journal = {IEEE Transactions on Geoscience and Remote Sensing (TGRS)},
number = {1}
}
@inproceedings{
title = {Task-adaptive Neural Process for User Cold-Start Recommendation},
type = {inproceedings},
year = {2021},
pages = {1306-1316},
publisher = {ACM / IW3C2},
id = {42ac31f3-a658-3c02-a8a9-afc537f02ca3},
created = {2021-06-15T12:45:27.421Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:46.899Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {DBLP:conf/www/Lin00PCW21},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
bibtype = {inproceedings},
author = {Lin, Xixun and Wu, Jia and Zhou, Chuan and Pan, Shirui and Cao, Yanan and Wang, Bin},
editor = {Leskovec, Jure and Grobelnik, Marko and Najork, Marc and Tang, Jie and Zia, Leila},
doi = {10.1145/3442381.3449908},
booktitle = {WWW '21: The Web Conference 2021, Virtual Event / Ljubljana, Slovenia, April 19-23, 2021}
}
@inproceedings{
title = {iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients},
type = {inproceedings},
year = {2021},
pages = {12557-12566 (CORE Ranked A*)},
id = {7fed38ad-d5cb-3a46-8ba4-e88a314a543b},
created = {2021-06-25T11:28:09.692Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:37.265Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Zhang2021},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
abstract = {\textitDifferentiable ARchiTecture Search (DARTS) has recently become the mainstream of neural architecture search (NAS) due to its efficiency and simplicity. With a gradient-based bi-level optimization, DARTS alternately optimizes the inner model weights and the outer architecture parameter in a weight-sharing supernet. A key challenge to the scalability and quality of the learned architectures is the need for differentiating through the inner-loop optimisation. While much has been discussed about several potentially fatal factors in DARTS, the architecture gradient, a.k.a. hypergradient, has received less attention. In this paper, we tackle the hypergradient computation in DARTS based on the implicit function theorem, making it only depends on the obtained solution to the inner-loop optimization and agnostic to the optimization path. To further reduce the computational requirements, we formulate a stochastic hypergradient approximation for differentiable NAS, and theoretically show that the architecture optimization with the proposed method, named iDARTS, is expected to converge to a stationary point. Comprehensive experiments on two NAS benchmark search spaces and the common NAS search space verify the effectiveness of our proposed method. It leads to architectures outperforming, with large margins, those learned by the baseline methods.},
bibtype = {inproceedings},
author = {Zhang, Miao and Su, Steven and Pan, Shirui and Chang, Xiaojun and Abbasnejad, Ehsan and Haffari, Reza},
booktitle = {International Conference on Machine Learning (ICML)}
}
@inproceedings{
title = {Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning},
type = {inproceedings},
year = {2021},
pages = {1477-1483 (CORE Ranked A*)},
id = {1595b0ab-94c6-3b12-a5fa-92712d20aa73},
created = {2021-06-25T11:28:09.695Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:38.107Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Jin2021},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
abstract = {Graph representation learning plays a vital role in processing graph-structured data. However, prior arts on graph representation learning heavily rely on the labeling information. To overcome this problem, inspired by the recent success of graph contrastive learning and Siamese networks in visual representation learning, we propose a novel self-supervised approach in this paper to learn node representations by enhancing Siamese self-distillation with multi-scale contrastive learning. Specifically, we first generate two augmented views from the input graph based on local and global perspectives. Then, we employ two objectives called cross-view and cross-network contrastiveness to maximize the agreement between node representations across different views and networks. To demonstrate the effectiveness of our approach, we perform empirical experiments on five real-world datasets. Our method not only achieves new state-of-the-art results but also surpasses some semi-supervised counterparts by large margins.},
bibtype = {inproceedings},
author = {Jin, Ming and Zheng, Yizhen and Li, Yuan-Fang and Gong, Chen and Zhou, Chuan and Pan, Shirui},
booktitle = {International Joint Conference on Artificial Intelligence, IJCAI}
}
@article{
title = {A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning},
type = {article},
year = {2021},
pages = {1},
id = {79c6139c-faea-3ec1-a7a2-1c53410e8fab},
created = {2021-08-13T11:48:35.560Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:52.198Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {9511798},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Jin, Di and Yu, Zhizhi and Jiao, Pengfei and Pan, Shirui and He, Dongxiao and Wu, Jia and Yu, Philip and Zhang, Weixiong},
doi = {10.1109/TKDE.2021.3104155},
journal = {IEEE Transactions on Knowledge and Data Engineering (TKDE)}
}
@article{
title = {Learning Graph Representations With Maximal Cliques},
type = {article},
year = {2021},
pages = {1-8},
id = {e234b8d1-4924-36b8-b619-323d8b79f500},
created = {2021-08-27T23:49:48.767Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:41.331Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {MolaeiTNNLS21},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Molaei, Soheila and Bousejin, Nima Ghanbari and Zare, Hadi and Jalili, Mahdi and Pan, Shirui},
doi = {10.1109/TNNLS.2021.3104901},
journal = {IEEE Transactions on Neural Networks and Learning Systems (TNNLS)}
}
@article{
title = {IGNSCDA: Predicting CircRNA-Disease Associations Based on Improved Graph Convolutional Network and Negative Sampling},
type = {article},
year = {2021},
pages = {1},
id = {3fd7b780-8674-3771-af65-49e630d01854},
created = {2021-09-22T07:29:55.591Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:43.242Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {9535297},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Lan, Wei and Dong, Yi and Chen, Qingfeng and Liu, Jin and Wang, Jianxin and Chen, Yi-Ping Phoebe and Pan, Shirui},
doi = {10.1109/TCBB.2021.3111607},
journal = {IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)}
}
@article{
title = {Learning Graph Neural Networks with Positive and Unlabeled Nodes},
type = {article},
year = {2021},
pages = {101:1--101:25},
volume = {15},
id = {53f20094-44b1-3213-9541-60d4f97d9792},
created = {2021-10-22T13:46:36.091Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:45.845Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {DBLP:journals/tkdd/WuPDZ21},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Wu, Man and Pan, Shirui and Du, Lan and Zhu, Xingquan},
doi = {10.1145/3450316},
journal = {ACM Transactions on Knowledge Discovery from Data (TKDD)},
number = {6}
}
@article{
title = {Anomaly Detection in Dynamic Graphs via Transformer},
type = {article},
year = {2021},
pages = {1-14},
id = {22a1edc8-2772-3941-8fdc-ac7cb60cf225},
created = {2021-10-29T10:19:54.175Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:44.208Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {liu-tkde-21},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Liu, Yixin and Pan, Shirui and Wang, Yu Guang and Xiong, Fei and Wang, Liang and Chen, Qingfeng and Lee, Vincent C S},
doi = {https://doi.org/10.1109/TKDE.2021.3124061},
journal = {IEEE Transactions on Knowledge and Data Engineering (TKDE)}
}
@inproceedings{
title = {Adapting Membership Inference Attacks to GNN for Graph Classification: Approaches and Implications},
type = {inproceedings},
year = {2021},
keywords = {-membership inference attacks,graph classifica-,graph neural networks,tion},
pages = {1421-1426 (CORE Ranked A*)},
id = {24ee3590-e438-3a2c-9af8-17d9246cb76b},
created = {2022-01-16T04:41:09.464Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:48.611Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Wu2021},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
abstract = {Graph Neural Networks (GNNs) are widely adopted to analyse non-Euclidean data, such as chemical networks, brain networks, and social networks, modelling complex relationships and interdependency between objects. Recently, Membership Inference Attack (MIA) against GNNs raises severe privacy concerns, where training data can be leaked from trained GNN models. However, prior studies focus on inferring the membership of only the components in a graph, e.g., an individual node or edge. How to infer the membership of an entire graph record is yet to be explored. In this paper, we take the first step in MIA against GNNs for graph-level classification. Our objective is to infer whether a graph sample has been used for training a GNN model. We present and implement two types of attacks, i.e., training-based attacks and threshold-based attacks from different adversarial capabilities. We perform comprehensive experiments to evaluate our attacks in seven real-world datasets using five representative GNN models. Both our attacks are shown effective and can achieve high performance, i.e., reaching over 0.7 attack F1 scores in most cases. Furthermore, we analyse the implications behind the MIA against GNNs. Our findings confirm that GNNs can be even more vulnerable to MIA than the models with non-graph structures. And unlike the node-level classifier, MIAs on graph-level classification tasks are more co-related with the overfitting level of GNNs rather than the statistic property of their training graphs.},
bibtype = {inproceedings},
author = {Wu, Bang and Yang, Xiangwen and Pan, Shirui and Yuan, Xingliang},
booktitle = {IEEE International Conference on Data Mining (ICDM)}
}
@inproceedings{
title = {Hypergraph Convolutional Network for Group Recommendation},
type = {inproceedings},
year = {2021},
pages = {260-269 (CORE Ranked A*)},
id = {bca7c1cf-819f-3ac8-bd14-1e5fca0b2532},
created = {2022-01-16T04:41:09.808Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:50.450Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {false},
hidden = {false},
citation_key = {Jia2021},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
bibtype = {inproceedings},
author = {Jia, Renqi and Zhou, Xiaofei and Dong, Linhua and Pan, Shirui},
booktitle = {IEEE International Conference on Data Mining (ICDM)}
}
@inproceedings{
title = {Contrastive Graph Poisson Networks: Semi-Supervised Learning with Extremely Limited Labels},
type = {inproceedings},
year = {2021},
volume = {34},
id = {0320713e-6414-3444-9a04-2080b45f140d},
created = {2022-04-10T12:15:00.977Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T23:32:40.699Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {wan2021contrastive},
source_type = {article},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d},
private_publication = {false},
bibtype = {inproceedings},
author = {Wan, Sheng and Zhan, Yibing and Liu, Liu and Yu, Baosheng and Pan, Shirui and Gong, Chen},
booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}
}
@article{
title = {Social Recommendation with Evolutionary Opinion Dynamics},
type = {article},
year = {2020},
keywords = {Evolutionary opinion dynamics,game theory,matrix factorization (MF),recommender systems,user influence},
pages = {3804-3816},
volume = {50},
id = {206c5a1b-6fd9-3cbc-94b1-ec58667d3640},
created = {2018-08-06T23:59:00.000Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:47.443Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Xiong2020},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
abstract = {When users in online social networks make a decision, they are often affected by their neighbors. Social recommendation models utilize social information to reveal the impact of neighbors on user preferences, and this impact is often described by the linear superposition of neighbor preferences or by global trust propagation. Further exploration needs to be undertaken to determine whether the influence pattern of other users from online interaction behaviors is adequately described. In this paper, we introduce evolutionary opinion dynamics from the field of statistical physics into recommender systems, characterizing the impact of other users. We propose an opinion dynamic model by evolutionary game theory. To describe online user interactions, we define the strategies during an interaction between two users, and present the payoff for each strategy in terms of errors of estimated ratings. Therefore, user behaviors are associated with their preferences and ratings. In addition, we measure user influence according to their topological roles in the social network. We incorporate evolutionary opinion dynamics and user influence into the recommendation framework for the prediction of unknown ratings. Experiment results on two real-world datasets demonstrate that our method outperforms state-of the-art models in terms of accuracy, and it also performs well for cold-start users. Our method reduces the divergence of user preferences, in accordance with online opinion interactions. Furthermore, our method has approximate computational complexity with matrix factorization, and results in less computation than state-of-the-art models. Our method is quite general, and indicates that studies in social physics, statistics, and other research fields may be involved in recommendation to improve the performance.},
bibtype = {article},
author = {Xiong, Fei and Wang, Ximeng and Pan, Shirui and Yang, Hong and Wang, Haishuai and Zhang, Chengqi},
doi = {10.1109/TSMC.2018.2854000},
journal = {IEEE Transactions on Systems, Man, and Cybernetics: Systems (TSMC)},
number = {10}
}
@inproceedings{
title = {Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks},
type = {inproceedings},
year = {2020},
keywords = {graph neural networks,graph structure learning,multivariate time series forecasting,spatial-temporal graphs},
pages = {753-763 (CORE Ranked A*)},
id = {74ce2213-b4f4-3435-831a-5f7652373efd},
created = {2020-11-06T23:59:00.000Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:33.348Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {false},
hidden = {false},
citation_key = {Wu2020a},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
abstract = {Modeling multivariate time series has long been a subject that has attracted researchers from a diverse range of fields including economics, finance, and traffic. A basic assumption behind multivariate time series forecasting is that its variables depend on one another but, upon looking closely, it is fair to say that existing methods fail to fully exploit latent spatial dependencies between pairs of variables. In recent years, meanwhile, graph neural networks (GNNs) have shown high capability in handling relational dependencies. GNNs require well-defined graph structures for information propagation which means they cannot be applied directly for multivariate time series where the dependencies are not known in advance. In this paper, we propose a general graph neural network framework designed specifically for multivariate time series data. Our approach automatically extracts the uni-directed relations among variables through a graph learning module, into which external knowledge like variable attributes can be easily integrated. A novel mix-hop propagation layer and a dilated inception layer are further proposed to capture the spatial and temporal dependencies within the time series. The graph learning, graph convolution, and temporal convolution modules are jointly learned in an end-to-end framework. Experimental results show that our proposed model outperforms the state-of-the-art baseline methods on 3 of 4 benchmark datasets and achieves on-par performance with other approaches on two traffic datasets which provide extra structural information.},
bibtype = {inproceedings},
author = {Wu, Zonghan and Pan, Shirui and Long, Guodong and Jiang, Jing and Chang, Xiaojun and Zhang, Chengqi},
doi = {10.1145/3394486.3403118},
booktitle = {Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)}
}
@article{
title = {Familial Clustering for Weakly-Labeled Android Malware Using Hybrid Representation Learning},
type = {article},
year = {2020},
keywords = {Android malware,machine learning,malware clustering,neural network},
pages = {3401-3414},
volume = {15},
id = {5f3303a0-75c2-3be4-afb3-eb6776411ab5},
created = {2019-10-27T23:59:00.000Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:44.842Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Zhang2020},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
abstract = {Labeling malware or malware clustering is important for identifying new security threats, triaging and building reference datasets. The state-of-the-art Android malware clustering approaches rely heavily on the raw labels from commercial AntiVirus (AV) vendors, which causes misclustering for a substantial number of weakly-labeled malware due to the inconsistent, incomplete and overly generic labels reported by these closed-source AV engines, whose capabilities vary greatly and whose internal mechanisms are opaque (i.e., intermediate detection results are unavailable for clustering). The raw labels are thus often used as the only important source of information for clustering. To address the limitations of the existing approaches, this paper presents Andre, a new ANDroid Hybrid REpresentation Learning approach to clustering weakly-labeled Android malware by preserving heterogeneous information from multiple sources (including the results of static code analysis, the meta-information of an app, and the raw-labels of the AV vendors) to jointly learn a hybrid representation for accurate clustering. The learned representation is then fed into our outlier-aware clustering to partition the weakly-labeled malware into known and unknown families. The malware whose malicious behaviours are close to those of the existing families on the network, are further classified using a three-layer Deep Neural Network (DNN). The unknown malware are clustered using a standard density-based clustering algorithm. We have evaluated our approach using 5,416 ground-truth malware from Drebin and 9,000 malware from VirusShare (uploaded between Mar. 2017 and Feb. 2018), consisting of 3324 weakly-labeled malware. The evaluation shows that Andre effectively clusters weakly-labeled malware which cannot be clustered by the state-of-the-art approaches, while achieving comparable accuracy with those approaches for clustering ground-truth samples.},
bibtype = {article},
author = {Zhang, Yanxin and Sui, Yulei and Pan, Shirui and Zheng, Zheng and Ning, Baodi and Tsang, Ivor and Zhou, Wanlei},
doi = {10.1109/TIFS.2019.2947861},
journal = {IEEE Transactions on Information Forensics and Security (TIFS)}
}
@article{
title = {Clustering social audiences in business information networks},
type = {article},
year = {2020},
keywords = {Business information networks,Clustering,Machine learning,Social networks},
pages = {107126},
volume = {100},
id = {2de224fd-7fc4-3bb8-b210-06b4a0e65cbe},
created = {2019-12-13T23:59:00.000Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:46.577Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {false},
hidden = {false},
folder_uuids = {032bc9cb-8256-40c2-a1d8-d016d563e89a,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
abstract = {Business information networks involve diverse users and rich content and have emerged as important platforms for enabling business intelligence and business decision making. A key step in an organizations business intelligence process is to cluster users with similar interests into social audiences and discover the roles they play within a business network. In this article, we propose a novel machine-learning approach, called CBIN, that co-clusters business information networks to discover and understand these audiences. The CBIN framework is based on co-factorization. The audience clusters are discovered from a combination of network structures and rich contextual information, such as node interactions and node-content correlations. Since what defines an audience cluster is data-driven, plus they often overlap, pre-determining the number of clusters is usually very difficult. Therefore, we have based CBIN on an overlapping clustering paradigm with a hold-out strategy to discover the optimal number of clusters given the underlying data. Experiments validate an outstanding performance by CBIN compared to other state-of-the-art algorithms on 13 real-world enterprise datasets.},
bibtype = {article},
author = {Zheng, Yu and Hu, Ruiqi and Fung, Sai fu and Yu, Celina and Long, Guodong and Guo, Ting and Pan, Shirui},
doi = {10.1016/j.patcog.2019.107126},
journal = {Pattern Recognition}
}
@article{
title = {Compact Scheduling for Task Graph Oriented Mobile Crowdsourcing},
type = {article},
year = {2020},
pages = {1},
id = {b5cd4d0d-a022-325b-bf82-ef7e5dba562b},
created = {2021-06-12T06:28:36.052Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2021-06-15T12:46:35.022Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {9268126},
source_type = {article},
folder_uuids = {a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Wang, Liang and Yu, Zhiwen and Han, Qi and Yang, Dingqi and Pan, Shirui and Yao, Yuan and Zhang, Daqing},
doi = {10.1109/TMC.2020.3040007},
journal = {IEEE Transactions on Mobile Computing (TMC)}
}
@article{
title = {Distributed Feature Selection for Big Data Using Fuzzy Rough Sets},
type = {article},
year = {2020},
pages = {846-857},
volume = {28},
id = {3389460a-0335-3b9c-b612-eec0280717b8},
created = {2021-06-12T06:28:36.121Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:40.992Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {8913637},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Kong, Linghe and Qu, Wenhao and Yu, Jiadi and Zuo, Hua and Chen, Guihai and Xiong, Fei and Pan, Shirui and Lin, Siyu and Qiu, Meikang},
doi = {10.1109/TFUZZ.2019.2955894},
journal = {IEEE Transactions on Fuzzy Systems (TFS)},
number = {5}
}
@article{
title = {Learning Graph Embedding With Adversarial Training Methods},
type = {article},
year = {2020},
pages = {2475-2487},
volume = {50},
id = {2a4e05e0-4e42-3051-8855-81187b32bad4},
created = {2021-06-12T06:28:37.145Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:45.646Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {8822591},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Pan, Shirui and Hu, Ruiqi and Fung, Sai-Fu and Long, Guodong and Jiang, Jing and Zhang, Chengqi},
doi = {10.1109/TCYB.2019.2932096},
journal = {IEEE Transactions on Cybernetics (TCYB)},
number = {6}
}
@article{
title = {Exploiting Implicit Influence From Information Propagation for Social Recommendation},
type = {article},
year = {2020},
pages = {4186-4199},
volume = {50},
id = {b7089a4b-7771-305e-a137-6db892735f94},
created = {2021-06-12T06:28:37.488Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:42.988Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {8846584},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Xiong, Fei and Shen, Weihan and Chen, Hongshu and Pan, Shirui and Wang, Ximeng and Yan, Zheng},
doi = {10.1109/TCYB.2019.2939390},
journal = {IEEE Transactions on Cybernetics (TCYB)},
number = {10}
}
@inproceedings{
title = {GSSNN: Graph Smoothing Splines Neural Networks},
type = {inproceedings},
year = {2020},
pages = {7007--7014 (CORE Ranked A*)},
id = {a42a8663-7bc5-3dbe-8f32-c947f0fa31e6},
created = {2021-06-15T12:45:26.633Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:50.211Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {aaai20-zhu},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
bibtype = {inproceedings},
author = {Zhu, Shichao and Zhou, Lewei and Pan, Shirui and Zhou, Chuan and Yan, Guiying and Wang, Bin},
booktitle = {Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI-20, New York, New York, USA, February 7-12, 2020}
}
@inproceedings{
title = {Grounding visual concepts for zero-shot Event Detection and Event Captioning},
type = {inproceedings},
year = {2020},
keywords = {Grounding Visual Concepts,Multimedia Event Captioning,Multimedia Event Detection,Zero-shot Learning},
pages = {297–305},
month = {8},
publisher = {Association for Computing Machinery (ACM)},
city = {United States of America},
id = {1cf5bb14-7c7b-36e1-8fc3-bf0e6c8eb8f1},
created = {2021-06-15T12:45:27.016Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2021-07-19T00:58:37.666Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {e59e737b5c8a44daa3d1ab8ea004104b},
source_type = {inproceedings},
notes = {ACM International Conference on Knowledge Discovery and Data Mining 2020, KDD\textquoteright20 ; Conference date: 23-08-2020 Through 27-08-2020},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d},
private_publication = {false},
abstract = {The flourishing of social media platforms requires techniques for understanding the content of media on a large scale. However, state-of-the art video event understanding approaches remain very limited in terms of their ability to deal with data sparsity, semantically unrepresentative event names, and lack of coherence between visual and textual concepts. Accordingly, in this paper, we propose a method of grounding visual concepts for large-scale Multimedia Event Detection (MED) and Multimedia Event Captioning (MEC) in zero-shot setting. More specifically, our framework composes the following: (1) deriving the novel semantic representations of events from their textual descriptions, rather than event names; (2) aggregating the ranks of grounded concepts for MED tasks. A statistical mean-shift outlier rejection model is proposed to remove the outlying concepts which are incorrectly grounded; and (3) defining MEC tasks and augmenting the MEC training set by the videos detected in MED in a zero-shot setting. To the best of our knowledge, this work is the first time to define and solve the MEC task, which is a further step towards understanding video events. We conduct extensive experiments and achieve state-of-the-art performance on the TRECVID MEDTest dataset, as well as our newly proposed TRECVID-MEC dataset.},
bibtype = {inproceedings},
author = {Li, Zhihui and Chang, Xiaojun and Yao, Lina and Pan, Shirui and Zongyuan, Ge and Zhang, Huaxiang},
editor = {Tang, Jiliang and Aditya Prakash, B},
doi = {10.1145/3394486.3403072},
booktitle = {Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD)}
}
@inproceedings{
title = {One-Shot Neural Architecture Search via Novelty Driven Sampling},
type = {inproceedings},
year = {2020},
pages = {3188--3194 (CORE Ranked A*)},
id = {b8053e6c-56a7-39e1-9dc4-fe40c08785ad},
created = {2021-06-15T12:45:27.746Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:36.753Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {zhangijcai20},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
bibtype = {inproceedings},
author = {Zhang, Miao and Li, Huiqi and Pan, Shirui and Liu, Taoping and Su, Steven},
booktitle = {International Joint Conference on Artificial Intelligence, IJCAI-20, Yokohama, Japan, January, 2021}
}
@inproceedings{
title = {Reinforcement Learning based Meta-path Discovery in Large-scale Heterogeneous Information Networks},
type = {inproceedings},
year = {2020},
pages = {6094--6101 (CORE Ranked A*)},
id = {963d8665-9303-3d4f-8d7a-010950da602a},
created = {2021-06-15T12:45:27.751Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:51.008Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {aaai20-wan},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
bibtype = {inproceedings},
author = {Wan, Guojia and Du, Bo and Pan, Shirui and Haffari, Gholamreza},
booktitle = {Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI-20, New York, New York, USA, February 7-12, 2020}
}
@inproceedings{
title = {Graph Stochastic Neural Networks for Semi-supervised Learning},
type = {inproceedings},
year = {2020},
pages = {19839--19848 (CORE Ranked A*; Top Conference in Ma},
id = {de9229d8-6e3f-3e52-81ea-bc98c14fe38d},
created = {2021-06-15T12:45:27.779Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:28.922Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {wangnips2020},
source_type = {inproceedings},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
bibtype = {inproceedings},
author = {Wang, Haibo and Zhou, Chuan and Chen, Xin and Wu, Jia and Pan, Shirui and Wang, Jilong},
booktitle = {Thirty-fourth Conference on Neural Information Processing Systems, NeurIPS-20, December 6-12, 2020, Virtual Conference}
}
@inproceedings{
title = {Overcoming Multi-Model Forgetting in One-Shot NAS with Diversity Maximization},
type = {inproceedings},
year = {2020},
pages = {7809--7818 (CORE Ranked A*)},
id = {2862ce87-c046-3ebc-89f4-ef78bf76cf30},
created = {2021-06-15T12:45:27.791Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:32.393Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {zhangcvpr2020},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
bibtype = {inproceedings},
author = {Zhang, Miao and Li, Huiqi and Pan, Shirui and Chang, Xiaojun and Su, Steven},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR-20}
}
@inproceedings{
title = {Reasoning Like Human: Hierarchical Reinforcement Learning for Knowledge Graph Reasoning},
type = {inproceedings},
year = {2020},
pages = {1926--1932 (CORE Ranked A*)},
id = {1339145a-9253-3c7f-902d-b314b4fc6a99},
created = {2021-06-15T12:45:28.083Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:37.615Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {wanijcai20},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
bibtype = {inproceedings},
author = {Wan, Guojia and Pan, Shirui and Gong, Chen and Zhou, Chuan and Haffari, Gholamreza},
booktitle = {International Joint Conference on Artificial Intelligence, IJCAI-20, Yokohama, Japan, January, 2021}
}
@inproceedings{
title = {OpenWGL: Open-World Graph Learning},
type = {inproceedings},
year = {2020},
pages = {681-690 (CORE Ranked A*; Best Student Paper Award)},
id = {fb08535d-dc6f-3ded-8a9e-47f28495b6f2},
created = {2021-06-15T12:45:28.468Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:31.583Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {wuicdm20},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
bibtype = {inproceedings},
author = {Wu, Man and Pan, Shirui and Zhu, Xingquan},
booktitle = {IEEE International Conference on Data Mining, ICDM-20, November 17-20, 2020, Sorrento, Italy}
}
@inproceedings{
title = {Cross-Graph: Robust and Unsupervised Embedding for Attributed Graphs with Corrupted Structure},
type = {inproceedings},
year = {2020},
pages = {571-580 (CORE Ranked A*)},
id = {9a705e4d-5d49-3b6b-9796-2f5384a5bfb0},
created = {2021-06-15T12:45:28.471Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:30.757Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {wangicdm20},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
bibtype = {inproceedings},
author = {Wang, Chun and Han, Bo and Pan, Shirui and Jiang, Jing and Niu, Gang and Long, Guodong},
booktitle = {IEEE International Conference on Data Mining, ICDM-20, November 17-20, 2020, Sorrento, Italy}
}
@inproceedings{
title = {Graph Geometry Interaction Learning},
type = {inproceedings},
year = {2020},
pages = {7548--7558 (CORE Ranked A*; Top Conference in Mach},
id = {7f9e66a5-9235-3a0d-90ee-606fe86cca06},
created = {2021-06-15T12:45:28.476Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:27.985Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {zhunips2020},
source_type = {inproceedings},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
bibtype = {inproceedings},
author = {Zhu, Shichao and Pan, Shirui and Zhou, Chuan and Wu, Jia and Cao, Yanan and Wang, Bin},
booktitle = {Thirty-fourth Conference on Neural Information Processing Systems, NeurIPS-20, December 6-12, 2020, Virtual Conference}
}
@inproceedings{
title = {Going Deep: Graph Convolutional Ladder-Shape Networks},
type = {inproceedings},
year = {2020},
pages = {2838--2845 (CORE Ranked A*)},
id = {75a7609d-1332-308e-a737-2db140b7cfc1},
created = {2021-06-15T12:45:28.502Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:49.370Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {aaai20-hu},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
bibtype = {inproceedings},
author = {Hu, Ruiqi and Pan, Shirui and Long, Guodong and Lu, Qinghua and Zhu, Liming and Jiang, Jing},
booktitle = {Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI-20, New York, New York, USA, February 7-12, 2020}
}
@inproceedings{
title = {A Relation-Specific Attention Network for Joint Entity and Relation Extraction},
type = {inproceedings},
year = {2020},
pages = {4054--4060 (CORE Ranked A*)},
id = {049c8fe7-45d3-34fb-bb08-38140f9bf813},
created = {2021-06-15T12:45:29.237Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:38.486Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {yuanijcai20},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
bibtype = {inproceedings},
author = {Yuan, Yue and Zhou, Xiaofei and Pan, Shirui and Zhu, Qiannan and Song, Zeliang and Guo, Li},
booktitle = {International Joint Conference on Artificial Intelligence, IJCAI-20, Yokohama, Japan, January, 2021}
}
@inproceedings{
title = {Unsupervised Domain Adaptive Graph Convolutional Networks},
type = {inproceedings},
year = {2020},
pages = {1457-1467 (CORE Ranked A*)},
id = {ba8a37c6-15e7-35ac-b729-072b339048d0},
created = {2021-06-15T12:45:29.245Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:48.503Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Wu2020},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
bibtype = {inproceedings},
author = {Wu, Man and Pan, Shirui and Zhou, Chuan and Chang, Xiaojun and Zhu, Xingquan},
doi = {10.1145/3366423.3380219 (CORE Ranked A*)},
booktitle = {The Web Conference (WWW), WWW-20, Taipei, Taiwan, April 20-24, 2020}
}
@inproceedings{
title = {Differentiable Neural Architecture Search in Equivalent Space with Exploration Enhancement},
type = {inproceedings},
year = {2020},
pages = {13341--13351 (CORE Ranked A*; Top Conference in Ma},
id = {55e9c148-7cdb-3b7a-aa8c-b75499ca6595},
created = {2021-06-15T12:45:29.250Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:29.802Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {zhangnips2020},
source_type = {inproceedings},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
bibtype = {inproceedings},
author = {Zhang, Miao and Li, Huiqi and Pan, Shirui and Chang, Xiaojun and Ge, Zongyuan and Su, Steven},
booktitle = {Thirty-fourth Conference on Neural Information Processing Systems, NeurIPS-20, December 6-12, 2020, Virtual Conference}
}
@inproceedings{
title = {Low-Bit Quantization for Attributed Network Representation Learning},
type = {inproceedings},
year = {2019},
pages = {4047-4053 (CORE Ranked A*)},
publisher = {ijcai.org},
id = {c6b64795-d583-35de-a7e5-4d6c9881d99b},
created = {2019-11-28T02:47:24.662Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:00.281Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {DBLP:conf/ijcai/YangP0Z019},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
abstract = {Attributed network embedding plays an important role in transferring network data into compact vectors for effective network analysis. Existing attributed network embedding models are designed either in continuous Euclidean spaces which introduce data redundancy or in binary coding spaces which incur significant loss of representation accuracy. To this end, we present a new Low-Bit Quantization for Attributed Network Representation Learning model (LQANR for short) that can learn compact node representations with low bitwidth values while preserving high representation accuracy. Specifically, we formulate a new representation learning function based on matrix factorization that can jointly learn the low-bit node representations and the layer aggregation weights under the low-bit quantization constraint. Because the new learning function falls into the category of mixed integer optimization, we propose an efficient mixed-integer based alternating direction method of multipliers (ADMM) algorithm as the solution. Experiments on real-world node classification and link prediction tasks validate the promising results of the proposed LQANR model.},
bibtype = {inproceedings},
author = {Yang, Hong and Pan, Shirui and Chen, Ling and Zhou, Chuan and Zhang, Peng},
editor = {Kraus, Sarit},
doi = {10.24963/ijcai.2019/562},
booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI 2019, Macao, China, August 10-16, 2019}
}
@article{
title = {Time series feature learning with labeled and unlabeled data},
type = {article},
year = {2019},
keywords = {Classification,Feature selection,Semi-supervised learning,Time series},
pages = {55-66},
volume = {89},
websites = {https://doi.org/10.1016/j.patcog.2018.12.026},
id = {2b45063f-2400-34f0-89f4-1414c481cd66},
created = {2019-11-28T02:47:24.972Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:53.404Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {DBLP:journals/pr/WangZWPC19},
source_type = {article},
folder_uuids = {032bc9cb-8256-40c2-a1d8-d016d563e89a,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
abstract = {Time series classification has attracted much attention in the last two decades. However, in many real-world applications, the acquisition of sufficient amounts of labeled training data is costly, while unlabeled data is usually easily to be obtained. In this paper, we study the problem of learning discriminative features (segments) from both labeled and unlabeled time series data. The discriminative segments are often referred to as shapelets. We present a new Semi-Supervised Shapelets Learning (SSSL for short) model to efficiently learn shapelets by using both labeled and unlabeled time series data. Briefly, SSSL engages both labeled and unlabeled time series data in an integrated model that considers the least squares regression, the power of the pseudo-labels, shapelets regularization, and spectral analysis. The experimental results on real-world data demonstrate the superiority of our approach over existing methods.},
bibtype = {article},
author = {Wang, Haishuai and Zhang, Qin and Wu, Jia and Pan, Shirui and Chen, Yixin},
doi = {10.1016/j.patcog.2018.12.026},
journal = {Pattern Recognition}
}
@inproceedings{
title = {Label Embedding with Partial Heterogeneous Contexts},
type = {inproceedings},
year = {2019},
pages = {4926-4933 (CORE Ranked A*)},
volume = {33},
publisher = {AAAI Press},
id = {15d3a253-620b-3b38-b38b-e3e7ea0cd100},
created = {2019-11-28T02:47:26.265Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:56.311Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {DBLP:conf/aaai/ShiXPTP19},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
abstract = {Label embedding plays an important role in many real-world applications. To enhance the label relatedness captured by the embeddings, multiple contexts can be adopted. However, these contexts are heterogeneous and often partially observed in practical tasks, imposing significant challenges to capture the overall relatedness among labels. In this paper, we propose a general Partial Heterogeneous Context Label Embedding (PHCLE) framework to address these challenges. Categorizing heterogeneous contexts into two groups, relational context and descriptive context, we design tailor-made matrix factorization formula to effectively exploit the label relatedness in each context. With a shared embedding principle across heterogeneous contexts, the label relatedness is selectively aligned in a shared space. Due to our elegant formulation, PHCLE overcomes the partial context problem and can nicely incorporate more contexts, which both cannot be tackled with existing multi-context label embedding methods. An effective alternative optimization algorithm is further derived to solve the sparse matrix factorization problem. Experimental results demonstrate that the label embeddings obtained with PHCLE achieve superb performance in image classification task and exhibit good interpretability in the downstream label similarity analysis and image understanding task.},
bibtype = {inproceedings},
author = {Shi, Yaxin and Xu, Donna and Pan, Yuangang and Tsang, Ivor W. and Pan, Shirui},
doi = {10.1609/aaai.v33i01.33014926},
booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence, AAAI}
}
@article{
title = {CFOND: Consensus Factorization for Co-Clustering Networked Data},
type = {article},
year = {2019},
keywords = {Networked data,co-clustering,networks,nonnegative matrix factorization,topology},
pages = {706-719},
volume = {31},
id = {c1e37698-4af5-3f9e-9653-c3da699e1bab},
created = {2019-11-28T02:47:26.590Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:55.296Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {DBLP:journals/tkde/GuoPZZ19},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
abstract = {Networked data are common in domains where instances are characterized by both feature values and inter-dependency relationships. Finding cluster structures for networked instances and discovering representative features for each cluster represent a special co-clustering task usefully for many real-world applications, such as automatic categorization of scientific publications and finding representative key-words for each cluster. To date, although co-clustering has been commonly used for finding clusters for both instances and features, all existing methods are focused on instance-feature values, without leveraging valuable topology relationships between instances to help boost co-clustering performance. In this paper, we propose CFOND, a consensus factorization based framework for co-clustering networked data. We argue that feature values and linkages provide useful information from different perspectives, but they are not always consistent and therefore need to be carefully aligned for best clustering results. In the paper, we advocate a consensus factorization principle, which simultaneously factorizes information from three aspects: network topology structures, instance-feature content relationships, and feature-feature correlations. The consensus factorization ensures that the final cluster structures are consistent across information from the three aspects with minimum errors. Experiments on real-life networks validate the performance of our algorithm.},
bibtype = {article},
author = {Guo, Ting and Pan, Shirui and Zhu, Xingquan and Zhang, Chengqi},
doi = {10.1109/TKDE.2018.2846555},
journal = {IEEE Transactions on Knowledge and Data Engineering (TKDE)},
number = {4}
}
@inproceedings{
title = {Graph wavenet for deep spatial-temporal graph modeling},
type = {inproceedings},
year = {2019},
pages = {1907-1913},
volume = {2019-Augus},
id = {8f2986ea-c327-3d4a-a436-779b53b600be},
created = {2019-11-28T02:47:27.940Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2021-06-25T11:50:20.586Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {false},
hidden = {false},
citation_key = {DBLP:journals/corr/abs-1906-00121},
source_type = {article},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d},
private_publication = {false},
abstract = {Spatial-temporal graph modeling is an important task to analyze the spatial relations and temporal trends of components in a system. Existing approaches mostly capture the spatial dependency on a fixed graph structure, assuming that the underlying relation between entities is pre-determined. However, the explicit graph structure (relation) does not necessarily reflect the true dependency and genuine relation may be missing due to the incomplete connections in the data. Furthermore, existing methods are ineffective to capture the temporal trends as the RNNs or CNNs employed in these methods cannot capture long-range temporal sequences. To overcome these limitations, we propose in this paper a novel graph neural network architecture, Graph WaveNet, for spatial-temporal graph modeling. By developing a novel adaptive dependency matrix and learn it through node embedding, our model can precisely capture the hidden spatial dependency in the data. With a stacked dilated 1D convolution component whose receptive field grows exponentially as the number of layers increases, Graph WaveNet is able to handle very long sequences. These two components are integrated seamlessly in a unified framework and the whole framework is learned in an end-to-end manner. Experimental results on two public traffic network datasets, METR-LA and PEMS-BAY, demonstrate the superior performance of our algorithm.},
bibtype = {inproceedings},
author = {Wu, Zonghan and Pan, Shirui and Long, Guodong and Jiang, Jing and Zhang, Chengqi},
doi = {10.24963/ijcai.2019/264},
booktitle = {IJCAI International Joint Conference on Artificial Intelligence}
}
@inproceedings{
title = {Attributed graph clustering: A deep attentional embedding approach},
type = {inproceedings},
year = {2019},
pages = {3670-3676},
volume = {2019-Augus},
id = {0e31878c-7720-3897-b1bf-7aafa2c6c129},
created = {2020-11-03T23:59:00.000Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2021-06-15T12:46:11.835Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {false},
hidden = {false},
citation_key = {Wang2019},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d},
private_publication = {false},
abstract = {Graph clustering is a fundamental task which discovers communities or groups in networks. Recent studies have mostly focused on developing deep learning approaches to learn a compact graph embedding, upon which classic clustering methods like k-means or spectral clustering algorithms are applied. These two-step frameworks are difficult to manipulate and usually lead to suboptimal performance, mainly because the graph embedding is not goal-directed, i.e., designed for the specific clustering task. In this paper, we propose a goal-directed deep learning approach, Deep Attentional Embedded Graph Clustering (DAEGC for short). Our method focuses on attributed graphs to sufficiently explore the two sides of information in graphs. By employing an attention network to capture the importance of the neighboring nodes to a target node, our DAEGC algorithm encodes the topological structure and node content in a graph to a compact representation, on which an inner product decoder is trained to reconstruct the graph structure. Furthermore, soft labels from the graph embedding itself are generated to supervise a self-training graph clustering process, which iteratively refines the clustering results. The self-training process is jointly learned and optimized with the graph embedding in a unified framework, to mutually benefit both components. Experimental results compared with state-of-the-art algorithms demonstrate the superiority of our method.},
bibtype = {inproceedings},
author = {Wang, Chun and Pan, Shirui and Hu, Ruiqi and Long, Guodong and Jiang, Jing and Zhang, Chengqi},
doi = {10.24963/ijcai.2019/509},
booktitle = {IJCAI International Joint Conference on Artificial Intelligence}
}
@inproceedings{
title = {Relation structure-aware heterogeneous graph neural network},
type = {inproceedings},
year = {2019},
keywords = {Coarsened line graph,Graph neural network,Heterogenous graph},
pages = {1534-1539 (CORE Ranked A*)},
volume = {2019-Novem},
id = {649203f8-2e36-3314-9d70-e43e6dba805c},
created = {2020-02-13T23:59:00.000Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:52.613Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Zhu2019},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
abstract = {Heterogeneous graphs with different types of nodes and edges are ubiquitous and have immense value in many applications. Existing works on modeling heterogeneous graphs usually follow the idea of splitting a heterogeneous graph into multiple homogeneous subgraphs. This is ineffective in exploiting hidden rich semantic associations between different types of edges for large-scale multi-relational graphs. In this paper, we propose Relation Structure-Aware Heterogeneous Graph Neural Network (RSHN), a unified model that integrates graph and its coarsened line graph to embed both nodes and edges in heterogeneous graphs without requiring any prior knowledge such as metapath. To tackle the heterogeneity of edge connections, RSHN first creates a Coarsened Line Graph Neural Network (CL-GNN) to excavate edge-centric relation structural features that respect the latent associations of different types of edges based on coarsened line graph. After that, a Heterogeneous Graph Neural Network (H-GNN) is used to leverage implicit messages from neighbor nodes and edges propagating among nodes in heterogeneous graphs. As a result, different types of nodes and edges can enhance their embedding through mutual integration and promotion. Experiments and comparisons, based on semi-supervised classification tasks on large scale heterogeneous networks with over a hundred types of edges, show that RSHN significantly outperforms state-of-the-arts.},
bibtype = {inproceedings},
author = {Zhu, Shichao and Zhou, Chuan and Pan, Shirui and Zhu, Xingquan and Wang, Bin},
doi = {10.1109/ICDM.2019.00203},
booktitle = {Proceedings - IEEE International Conference on Data Mining, ICDM}
}
@inproceedings{
title = {Domain-adversarial graph neural networks for text classification},
type = {inproceedings},
year = {2019},
keywords = {Cross-domain learning,Graph neural networks,Text classification},
pages = {648-657 (CORE Ranked A*)},
volume = {2019-Novem},
id = {a5af5826-9b18-3360-9de5-26d4e6f78b87},
created = {2020-02-13T23:59:00.000Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:51.778Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {false},
hidden = {false},
citation_key = {Wu2019},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
abstract = {© 2019 IEEE. Text classification, in cross-domain setting, is a challenging task. On the one hand, data from other domains are often useful to improve the learning on the target domain; on the other hand, domain variance and hierarchical structure of documents from words, key phrases, sentences, paragraphs, etc. make it difficult to align domains for effective learning. To date, existing cross-domain text classification methods mainly strive to minimize feature distribution differences between domains, and they typically suffer from three major limitations - (1) difficult to capture semantics in non-consecutive phrases and long-distance word dependency because of treating texts as word sequences, (2) neglect of hierarchical coarse-grained structures of document for feature learning, and (3) narrow focus of the domains at instance levels, without using domains as supervisions to improve text classification. This paper proposes an end-to-end, domain-adversarial graph neural networks (DAGNN), for cross-domain text classification. Our motivation is to model documents as graphs and use a domain-adversarial training principle to lean features from each graph (as well as learning the separation of domains) for effective text classification. At the instance level, DAGNN uses a graph to model each document, so that it can capture non-consecutive and long-distance semantics. At the feature level, DAGNN uses graphs from different domains to jointly train hierarchical graph neural networks in order to learn good features. At the learning level, DAGNN proposes a domain-adversarial principle such that the learned features not only optimally classify documents but also separates domains. Experiments on benchmark datasets demonstrate the effectiveness of our method in cross-domain classification tasks.},
bibtype = {inproceedings},
author = {Wu, M. and Pan, S. and Zhu, X. and Zhou, C. and Pan, L.},
doi = {10.1109/ICDM.2019.00075},
booktitle = {Proceedings - IEEE International Conference on Data Mining, ICDM}
}
@article{
title = {Cost-Sensitive Parallel Learning Framework for Insurance Intelligence Operation},
type = {article},
year = {2019},
pages = {9713-9723},
volume = {66},
id = {1b63652b-4960-3915-978e-0b07882feafe},
created = {2021-06-12T06:28:37.534Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:10:54.338Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {8488663},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Jiang, Xinxin and Pan, Shirui and Long, Guodong and Xiong, Fei and Jiang, Jing and Zhang, Chengqi},
doi = {10.1109/TIE.2018.2873526},
journal = {IEEE Transactions on Industrial Electronics (TIE)},
number = {12}
}
@inproceedings{
title = {Active discriminative network representation learning},
type = {inproceedings},
year = {2018},
pages = {2142-2148 (CORE Ranked A*)},
volume = {2018-July},
month = {7},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
city = {California},
id = {8fe36a1f-52c9-3b65-a1eb-c35aaf08e00a},
created = {2018-07-21T08:24:49.331Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:06.387Z},
read = {true},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Gao2018},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
abstract = {Most of current network representation models are learned in unsupervised fashions, which usually lack the capability of discrimination when applied to network analysis tasks, such as node classification. It is worth noting that label information is valuable for learning the discriminative network representations. However, labels of all training nodes are always difficult or expensive to obtain and manually labeling all nodes for training is inapplicable. Different sets of labeled nodes for model learning lead to different network representation results. In this paper, we propose a novel method, termed as ANRMAB, to learn the active discriminative network representations with a multi-armed bandit mechanism in active learning setting. Specifically, based on the networking data and the learned network representations, we design three active learning query strategies. By deriving an effective reward scheme that is closely related to the estimated performance measure of interest, ANRMAB uses a multi-armed bandit mechanism for adaptive decision making to select the most informative nodes for labeling. The updated labeled nodes are then used for further discriminative network representation learning. Experiments are conducted on three public data sets to verify the effectiveness of ANRMAB.},
bibtype = {inproceedings},
author = {Gao, Li and Yang, Hong and Zhou, Chuan and Wu, Jia and Pan, Shirui and Hu, Yue},
doi = {10.24963/ijcai.2018/296},
booktitle = {IJCAI International Joint Conference on Artificial Intelligence, IJCAI}
}
@inproceedings{
title = {Discrete network embedding},
type = {inproceedings},
year = {2018},
pages = {3549-3555 (CORE Ranked A*)},
volume = {2018-July},
month = {7},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
city = {California},
id = {6a0c53c8-c661-3190-ad98-0ba086c8adb9},
created = {2018-07-21T08:25:44.116Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:08.064Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Shen2018},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
abstract = {Network embedding aims to seek low-dimensional vector representations for network nodes, by preserving the network structure. The network embedding is typically represented in continuous vector, which imposes formidable challenges in storage and computation costs, particularly in large-scale applications. To address the issue, this paper proposes a novel discrete network embedding (DNE) for more compact representations. In particular, DNE learns short binary codes to represent each node. The Hamming similarity between two binary embeddings is then employed to well approximate the ground-truth similarity. A novel discrete multi-class classifier is also developed to expedite classification. Moreover, we propose to jointly learn the discrete embedding and classifier within a unified framework to improve the compactness and discrimination of network embedding. Extensive experiments on node classification consistently demonstrate that DNE exhibits lower storage and computational complexity than state-of-the-art network embedding methods, while obtains competitive classification results.},
bibtype = {inproceedings},
author = {Shen, Xiaobo and Pan, Shirui and Liu, Weiwei and Ong, Yew Soon and Sun, Quan Sen},
doi = {10.24963/ijcai.2018/493},
booktitle = {IJCAI International Joint Conference on Artificial Intelligence, IJCAI}
}
@inproceedings{
title = {Adversarially regularized graph autoencoder for graph embedding},
type = {inproceedings},
year = {2018},
pages = {2609-2615 (CORE Ranked A*)},
volume = {2018-July},
month = {7},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
city = {California},
id = {62ab7b56-0618-3c35-92bf-f06b05304681},
created = {2018-07-21T08:26:19.554Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:07.240Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Pan2018},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
abstract = {Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction errors of graph data, but they have mostly ignored the data distribution of the latent codes from the graphs, which often results in inferior embedding in real-world graph data. In this paper, we propose a novel adversarial graph embedding framework for graph data. The framework encodes the topological structure and node content in a graph to a compact representation, on which a decoder is trained to reconstruct the graph structure. Furthermore, the latent representation is enforced to match a prior distribution via an adversarial training scheme. To learn a robust embedding, two variants of adversarial approaches, adversarially regularized graph autoencoder (ARGA) and adversarially regularized variational graph autoencoder (ARVGA), are developed. Experimental studies on real-world graphs validate our design and demonstrate that our algorithms outperform baselines by a wide margin in link prediction, graph clustering, and graph visualization tasks.},
bibtype = {inproceedings},
author = {Pan, Shirui and Hu, Ruiqi and Long, Guodong and Jiang, Jing and Yao, Lina and Zhang, Chengqi},
doi = {10.24963/ijcai.2018/362},
booktitle = {IJCAI International Joint Conference on Artificial Intelligence, IJCAI}
}
@inproceedings{
title = {Binarized attributed network embedding},
type = {inproceedings},
year = {2018},
keywords = {Attributed network embedding,Learning to hash,Weisfeiler-Lehman graph kernels},
pages = {1476-1481 (CORE Ranked A*)},
volume = {2018-Novem},
publisher = {IEEE Computer Society},
id = {9dddf43e-efb8-39a9-a1f2-db212fbd4749},
created = {2019-11-28T02:47:21.403Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:05.478Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {DBLP:conf/icdm/YangP00LZ18},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
abstract = {Attributed network embedding enables joint representation learning of node links and attributes. Existing attributed network embedding models are designed in continuous Euclidean spaces which often introduce data redundancy and impose challenges to storage and computation costs. To this end, we present a Binarized Attributed Network Embedding model (BANE for short) to learn binary node representation. Specifically, we define a new Weisfeiler-Lehman proximity matrix to capture data dependence between node links and attributes by aggregating the information of node attributes and links from neighboring nodes to a given target node in a layer-wise manner. Based on the Weisfeiler-Lehman proximity matrix, we formulate a new Weisfiler-Lehman matrix factorization learning function under the binary node representation constraint. The learning problem is a mixed integer optimization and an efficient cyclic coordinate descent (CCD) algorithm is used as the solution. Node classification and link prediction experiments on real-world datasets show that the proposed BANE model outperforms the state-of-the-art network embedding methods.},
bibtype = {inproceedings},
author = {Yang, Hong and Pan, Shirui and Zhang, Peng and Chen, Ling and Lian, Defu and Zhang, Chengqi},
doi = {10.1109/ICDM.2018.8626170},
booktitle = {Proceedings - IEEE International Conference on Data Mining, ICDM}
}
@inproceedings{
title = {DISAN: Directional self-attention network for RnN/CNN-free language understanding},
type = {inproceedings},
year = {2018},
pages = {5446-5455},
publisher = {AAAI Press},
id = {71f6ca74-e2ef-3b06-b531-e94e9cd5a485},
created = {2019-11-28T02:47:23.659Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:04.673Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {DBLP:conf/aaai/ShenZLJPZ18},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
abstract = {Recurrent neural nets (RNN) and convolutional neural nets (CNN) are widely used on NLP tasks to capture the long-term and local dependencies, respectively. Attention mechanisms have recently attracted enormous interest due to their highly parallelizable computation, significantly less training time, and flexibility in modeling dependencies. We propose a novel attention mechanism in which the attention between elements from input sequence(s) is directional and multi-dimensional (i.e., feature-wise). A light-weight neural net, “Directional Self-Attention Network (DiSAN)”, is then proposed to learn sentence embedding, based solely on the proposed attention without any RNN/CNN structure. DiSAN is only composed of a directional self-attention with temporal order encoded, followed by a multi-dimensional attention that compresses the sequence into a vector representation. Despite its simple form, DiSAN outperforms complicated RNN models on both prediction quality and time efficiency. It achieves the best test accuracy among all sentence encoding methods and improves the most recent best result by 1.02% on the Stanford Natural Language Inference (SNLI) dataset, and shows state-of-the-art test accuracy on the Stanford Sentiment Treebank (SST), Multi-Genre natural language inference (MultiNLI), Sentences Involving Compositional Knowledge (SICK), Customer Review, MPQA, TREC question-type classification and Subjectivity (SUBJ) datasets.},
bibtype = {inproceedings},
author = {Shen, Tao and Jiang, Jing and Zhou, Tianyi and Pan, Shirui and Long, Guodong and Zhang, Chengqi},
editor = {McIlraith, Sheila A and Weinberger, Kilian Q},
booktitle = {32nd AAAI Conference on Artificial Intelligence, AAAI 2018}
}
@article{
title = {Multiple structure-view learning for graph classification},
type = {article},
year = {2018},
keywords = {Graph,graph classification,multiview learning,subgraph mining},
pages = {3236-3251},
volume = {29},
id = {78a05005-0123-3702-a914-194091b99774},
created = {2019-11-28T02:47:23.972Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:02.882Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {DBLP:journals/tnn/WuPZZY18},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
abstract = {Many applications involve objects containing structure and rich content information, each describing different feature aspects of the object. Graph learning and classification is a common tool for handling such objects. To date, existing graph classification has been limited to the single-graph setting with each object being represented as one graph from a single structure-view. This inherently limits its use to the classification of complicated objects containing complex structures and uncertain labels. In this paper, we advance graph classification to handle multigraph learning for complicated objects from multiple structure views, where each object is represented as a bag containing several graphs and the label is only available for each graph bag but not individual graphs inside the bag. To learn such graph classification models, we propose a multistructure-view bag constrained learning (MSVBL) algorithm, which aims to explore substructure features across multiple structure views for learning. By enabling joint regularization across multiple structure views and enforcing labeling constraints at the bag and graph levels, MSVBL is able to discover the most effective substructure features across all structure views. Experiments and comparisons on real-world data sets validate and demonstrate the superior performance of MSVBL in representing complicated objects as multigraph for classification, e.g., MSVBL outperforms the state-of-the-art multiview graph classification and multiview multi-instance learning approaches.},
bibtype = {article},
author = {Wu, Jia and Pan, Shirui and Zhu, Xingquan and Zhang, Chengqi and Yu, Philip S.},
doi = {10.1109/TNNLS.2017.2703832},
journal = {IEEE Transactions on Neural Networks and Learning Systems (TNNLS)},
number = {7}
}
@article{
title = {Hashing for Adaptive Real-Time Graph Stream Classification with Concept Drifts},
type = {article},
year = {2018},
keywords = {Cliques,concept drifts,graph stream classification,hashing},
pages = {1591-1604},
volume = {48},
id = {6c2a7132-5e69-3be3-86e1-4e2f7f1afa9c},
created = {2019-11-28T02:47:26.169Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:01.074Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {DBLP:journals/tcyb/ChiLZPC18},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
abstract = {Many applications involve processing networked streaming data in a timely manner. Graph stream classification aims to learn a classification model from a stream of graphs with only one-pass of data, requiring real-time processing in training and prediction. This is a nontrivial task, as many existing methods require multipass of the graph stream to extract subgraph structures as features for graph classification which does not simultaneously satisfy 'one-pass' and 'real-time' requirements. In this paper, we propose an adaptive real-time graph stream classification method to address this challenge. We partition the unbounded graph stream data into consecutive graph chunks, each consisting of a fixed number of graphs and delivering a corresponding chunk-level classifier. We employ a random hashing function to compress the original node set of graphs in each chunk for fast feature detection when training chunk-level classifiers. Furthermore, a differential hashing strategy is applied to map unlimited increasing features (i.e., cliques) into a fixed-size feature space which is then used as a feature vector for stochastic learning. Finally, the chunk-level classifiers are weighted in an ensemble learning model for graph classification. The proposed method substantially speeds up the graph feature extraction and avoids unbounded graph feature growth. Moreover, it effectively offsets concept drifts in graph stream classification. Experiments on real-world and synthetic graph streams demonstrate that our method significantly outperforms existing methods in both classification accuracy and learning efficiency.},
bibtype = {article},
author = {Chi, Lianhua and Li, Bin and Zhu, Xingquan and Pan, Shirui and Chen, Ling},
doi = {10.1109/TCYB.2017.2708979},
journal = {IEEE Transactions on Cybernetics (TCYB)},
number = {5}
}
@article{
title = {Multi-instance learning with discriminative bag mapping},
type = {article},
year = {2018},
keywords = {Bag mapping,Classification,Instance selection,Multi-instance learning},
pages = {1065-1080},
volume = {30},
id = {527bff30-c159-30bf-89fa-c2b10e10b8f8},
created = {2019-11-28T02:47:26.247Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:01.930Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {DBLP:journals/tkde/WuPZZW18},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
abstract = {Multi-instance learning (MIL) is a useful tool for tackling labeling ambiguity in learning because it allows a bag of instances to share one label. Bag mapping transforms a bag into a single instance in a new space via instance selection and has drawn significant attention recently. To date, most existing work is based on the original space, using all instances inside each bag for bag mapping, and the selected instances are not directly tied to an MIL objective. As a result, it is difficult to guarantee the distinguishing capacity of the selected instances in the new bag mapping space. In this paper, we propose a discriminative mapping approach for multi-instance learning (MILDM) that aims to identify the best instances to directly distinguish bags in the new mapping space. Accordingly, each instance bag can be mapped using the selected instances to a new feature space, and hence any generic learning algorithm, such as an instance-based learning algorithm, can be used to derive learning models for multi-instance classification. Experiments and comparisons on eight different types of real-world learning tasks (including 14 data sets) demonstrate that MILDM outperforms the state-of-The-Art bag mapping multi-instance learning approaches. Results also confirm that MILDM achieves balanced performance between runtime efficiency and classification effectiveness.},
bibtype = {article},
author = {Wu, Jia and Pan, Shirui and Zhu, Xingquan and Zhang, Chengqi and Wu, Xindong},
doi = {10.1109/TKDE.2017.2788430},
journal = {IEEE Transactions on Knowledge and Data Engineering (TKDE)},
number = {6}
}
@article{
title = {A Three-Layered Mutually Reinforced Model for Personalized Citation Recommendation},
type = {article},
year = {2018},
keywords = {Mutually reinforced model,personalized citation recommendation,three-layered interactive clustering},
pages = {6026-6037},
volume = {29},
id = {a0411f9a-ce3c-33e2-91e2-f9d3ef1545af},
created = {2019-11-28T02:47:26.597Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:03.730Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {DBLP:journals/tnn/CaiHLZPY18},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
abstract = {Fast-growing scientific papers pose the problem of rapidly and accurately finding a list of reference papers for a given manuscript. Citation recommendation is an indispensable technique to overcome this obstacle. In this paper, we propose a citation recommendation approach via mutual reinforcement on a three-layered graph, in which each paper, author or venue is represented as a vertex in the paper layer, author layer, and venue layer, respectively. For personalized recommendation, we initiate the random walk separately for each query researcher. However, this has a high computational complexity due to the large graph size. To solve this problem, we apply a three-layered interactive clustering approach to cluster related vertices in the graph. Personalized citation recommendations are then made on the subgraph, generated by the clusters associated with each researcher's needs. When evaluated on the ACL anthology network, DBLP, and CiteSeer ML data sets, the performance of our proposed model-based citation recommendation approach is comparable with that of other state-of-the-art citation recommendation approaches. The results also demonstrate that the personalized recommendation approach is more effective than the nonpersonalized recommendation approach.},
bibtype = {article},
author = {Cai, Xiaoyan and Han, Junwei and Li, Wenjie and Zhang, Renxian and Pan, Shirui and Yang, Libin},
doi = {10.1109/TNNLS.2018.2817245},
journal = {IEEE Transactions on Neural Networks and Learning Systems (TNNLS)},
number = {12}
}
@article{
title = {Positive and Unlabeled Multi-Graph Learning},
type = {article},
year = {2017},
keywords = {Classification,Graph,features,multi-instance (MI),positive and unlabeled (PU) learning,subgraph},
pages = {818-829},
volume = {47},
id = {2269dd2c-5041-3189-b532-828de638e48a},
created = {2019-11-28T02:47:23.322Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:09.767Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {DBLP:journals/tcyb/WuPZZW17},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
abstract = {In this paper, we advance graph classification to handle multi-graph learning for complicated objects, where each object is represented as a bag of graphs and the label is only available to each bag but not individual graphs. In addition, when training classifiers, users are only given a handful of positive bags and many unlabeled bags, and the learning objective is to train models to classify previously unseen graph bags with maximum accuracy. To achieve the goal, we propose a positive and unlabeled multi-graph learning (puMGL) framework to first select informative subgraphs to convert graphs into a feature space. To utilize unlabeled bags for learning, puMGL assigns a confidence weight to each bag and dynamically adjusts its weight value to select 'reliable negative bags.' A number of representative graphs, selected from positive bags and identified reliable negative graph bags, form a 'margin graph pool' which serves as the base for deriving subgraph patterns, training graph classifiers, and further updating the bag weight values. A closed-loop iterative process helps discover optimal subgraphs from positive and unlabeled graph bags for learning. Experimental comparisons demonstrate the performance of puMGL for classifying real-world complicated objects.},
bibtype = {article},
author = {Wu, Jia and Pan, Shirui and Zhu, Xingquan and Zhang, Chengqi and Wu, Xindong},
doi = {10.1109/TCYB.2016.2527239},
journal = {IEEE Transactions on Cybernetics (TCYB)},
number = {4}
}
@article{
title = {Task Sensitive Feature Exploration and Learning for Multitask Graph Classification},
type = {article},
year = {2017},
keywords = {Feature selection,graph classification,multitask learning (MTL),subgraph mining,supervised learning},
pages = {744-758},
volume = {47},
id = {40c284f9-0ea2-37cc-8a78-2058d5d65c5f},
created = {2019-11-28T02:47:24.255Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:08.880Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {DBLP:journals/tcyb/PanWZLZ17},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
abstract = {Multitask learning (MTL) is commonly used for jointly optimizing multiple learning tasks. To date, all existing MTL methods have been designed for tasks with feature-vector represented instances, but cannot be applied to structure data, such as graphs. More importantly, when carrying out MTL, existing methods mainly focus on exploring overall commonality or disparity between tasks for learning, but cannot explicitly capture task relationships in the feature space, so they are unable to answer important questions, such as what exactly is shared between tasks and what is the uniqueness of one task differing from others? In this paper, we formulate a new multitask graph learning problem, and propose a task sensitive feature exploration and learning algorithm for multitask graph classification. Because graphs do not have features available, we advocate a task sensitive feature exploration and learning paradigm to jointly discover discriminative subgraph features across different tasks. In addition, a feature learning process is carried out to categorize each subgraph feature into one of three categories: 1) common feature; 2) task auxiliary feature; and 3) task specific feature, indicating whether the feature is shared by all tasks, by a subset of tasks, or by only one specific task, respectively. The feature learning and the multiple task learning are iteratively optimized to form a multitask graph classification model with a global optimization goal. Experiments on real-world functional brain analysis and chemical compound categorization demonstrate the algorithm's performance. Results confirm that our method can be used to explicitly capture task correlations and uniqueness in the feature space, and explicitly answer what are shared between tasks and what is the uniqueness of a specific task.},
bibtype = {article},
author = {Pan, Shirui and Wu, Jia and Zhu, Xingquan and Long, Guodong and Zhang, Chengqi},
doi = {10.1109/TCYB.2016.2526058},
journal = {IEEE Transactions on Cybernetics (TCYB)},
number = {3}
}
@article{
title = {Exploiting Attribute Correlations: A Novel Trace Lasso-Based Weakly Supervised Dictionary Learning Method},
type = {article},
year = {2017},
pages = {4497-4508},
volume = {47},
id = {40633cfa-50b9-3bd6-b29c-77d41f1d5f7c},
created = {2021-06-12T06:28:36.741Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:10.619Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {7582406},
source_type = {article},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
bibtype = {article},
author = {Wu, Lin and Wang, Yang and Pan, Shirui},
doi = {10.1109/TCYB.2016.2612686},
journal = {IEEE Transactions on Cybernetics (TCYB)},
number = {12}
}
@article{
title = {Joint Structure Feature Exploration and Regularization for Multi-Task Graph Classification},
type = {article},
year = {2016},
keywords = {Graph Classification,Multi-task Learning,Regularization,Subgraph Features,Supervised Learning},
pages = {715-728},
volume = {28},
month = {3},
publisher = {IEEE Computer Society},
day = {1},
id = {f46e588c-385f-3617-84f5-5712f6bbc9b3},
created = {2016-04-29T05:47:43.000Z},
accessed = {2016-04-29},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:14.735Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Pan2016a},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
abstract = {Graph classification aims to learn models to classify structure data. To date, all existing graph classification methods are designed to target one single learning task and require a large number of labeled samples for learning good classification models. In reality, each real-world task may only have a limited number of labeled samples, yet multiple similar learning tasks can provide useful knowledge to benefit all tasks as a whole. In this paper, we formulate a new multi-task graph classification (MTG) problem, where multiple graph classification tasks are jointly regularized to find discriminative subgraphs shared by all tasks for learning. The niche of MTG stems from the fact that with a limited number of training samples, subgraph features selected for one single graph classification task tend to overfit the training data. By using additional tasks as evaluation sets, MTG can jointly regularize multiple tasks to explore high quality subgraph features for graph classification. To achieve this goal, we formulate an objective function which combines multiple graph classification tasks to evaluate the informativeness score of a subgraph feature. An iterative subgraph feature exploration and multi-task learning process is further proposed to incrementally select subgraph features for graph classification. Experiments on real-world multi-task graph classification datasets demonstrate significant performance gain.},
bibtype = {article},
author = {Pan, Shirui and Wu, Jia and Zhu, Xingquan and Zhang, Chengqi and Yu, Philip S.},
doi = {10.1109/TKDE.2015.2492567},
journal = {IEEE Transactions on Knowledge and Data Engineering (TKDE)},
number = {3}
}
@article{
title = {SODE: Self-Adaptive One-Dependence Estimators for classification},
type = {article},
year = {2016},
keywords = {Artificial immune systems,Attribute weighting,Classification,Evolutionary machine learning,Naive Bayes,Self-adaptive},
pages = {358-377},
volume = {51},
websites = {http://www.scopus.com/inward/record.url?eid=2-s2.0-84955724165&partnerID=tZOtx3y1},
month = {3},
publisher = {Elsevier Ltd},
id = {f78995da-def4-3faa-90cc-167dcef1881c},
created = {2016-04-29T05:47:43.000Z},
accessed = {2016-04-29},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:13.015Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Wu2016a},
folder_uuids = {032bc9cb-8256-40c2-a1d8-d016d563e89a,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
abstract = {SuperParent-One-Dependence Estimators (SPODEs) represent a family of semi-naive Bayesian classifiers which relax the attribute independence assumption of Naive Bayes (NB) to allow each attribute to depend on a common single attribute (superparent). SPODEs can effectively handle data with attribute dependency but still inherent NB's key advantages such as computational efficiency and robustness for high dimensional data. In reality, determining an optimal superparent for SPODEs is difficult. One common approach is to use weighted combinations of multiple SPODEs, each having a different superparent with a properly assigned weight value (i.e., a weight value is assigned to each attribute). In this paper, we propose a self-adaptive SPODEs, namely SODE, which uses immunity theory in artificial immune systems to automatically and self-adaptively select the weight for each single SPODE. SODE does not need to know the importance of individual SPODE nor the relevance among SPODEs, and can flexibly and efficiently search optimal weight values for each SPODE during the learning process. Extensive experiments and comparisons on 56 benchmark data sets, and validations on image and text classification, demonstrate that SODE outperforms state-of-the-art weighted SPODE algorithms and is suitable for a wide range of learning tasks. Results also confirm that SODE provides an appropriate balance between runtime efficiency and accuracy.},
bibtype = {article},
author = {Wu, Jia and Pan, Shirui and Zhu, Xingquan and Zhang, Peng and Zhang, Chengqi},
doi = {10.1016/j.patcog.2015.08.023},
journal = {Pattern Recognition}
}
@inproceedings{
title = {Tri-party deep network representation},
type = {inproceedings},
year = {2016},
pages = {1895-1901},
volume = {2016-Janua},
publisher = {AAAI},
id = {4d4c0ae3-6c38-3032-a569-dccd7ef6d0d6},
created = {2016-05-13T07:16:08.000Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2021-06-15T12:46:21.164Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {PanIJCAI2016},
source_type = {inproceedings},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d},
private_publication = {false},
abstract = {Information network mining often requires examination of linkage relationships between nodes for analysis. Recently, network representation has emerged to represent each node in a vector format, embedding network structure, so off-the-shelf machine learning methods can be directly applied for analysis. To date, existing methods only focus on one aspect of node information and cannot leverage node labels. In this paper, we propose TriDNR, a tri-party deep network representation model, using information from three parties: node structure, node content, and node labels (if available) to jointly learn optimal node representation. TriDNR is based on our new coupled deep natural language module, whose learning is enforced at three levels: (1) at the network structure level, TriDNR exploits inter-node relationship by maximizing the probability of observing surrounding nodes given a node in random walks; (2) at the node content level, TriDNR captures node-word correlation by maximizing the co-occurrence of word sequence given a node; and (3) at the node label level, TriDNR models label-word correspondence by maximizing the probability of word sequence given a class label. The tri-party information is jointly fed into the neural network model to mutually enhance each other to learn optimal representation, and results in up to 79% classification accuracy gain, compared to state-of-the-art methods.},
bibtype = {inproceedings},
author = {Pan, Shirui and Wu, Jia and Zhu, Xingquan and Zhang, Chengqi and Wang, Yang},
booktitle = {IJCAI International Joint Conference on Artificial Intelligence}
}
@inproceedings{
title = {Iterative views agreement: An iterative low-rank based structured optimization method to multi-view spectral clustering},
type = {inproceedings},
year = {2016},
volume = {2016-Janua},
id = {9a613a2a-ee86-30b1-9068-234c05440f3b},
created = {2017-12-13T00:56:25.187Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2021-06-15T12:46:20.416Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {false},
hidden = {false},
citation_key = {Wang2016},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d},
private_publication = {false},
abstract = {Multi-view spectral clustering, which aims at yielding an agreement or consensus data objects grouping across multi-views with their graph laplacian matrices, is a fundamental clustering problem. Among the existing methods, Low-Rank Representation (LRR) based method is quite superior in terms of its effectiveness, intuitiveness and robustness to noise corruptions. However, it aggressively tries to learn a common low-dimensional subspace for multi-view data, while inattentively ignoring the local manifold structure in each view, which is critically important to the spectral clustering; worse still, the low-rank minimization is enforced to achieve the data correlation consensus among all views, failing to flexibly preserve the local manifold structure for each view. In this paper, 1) we propose a multi-graph laplacian regularized LRR with each graph laplacian corresponding to one view to characterize its local manifold structure. 2) Instead of directly enforcing the low-rank minimization among all views for correlation consensus, we separately impose low-rank constraint on each view, coupled with a mutual structural consensus constraint, where it is able to not only well preserve the local manifold structure but also serve as a constraint for that from other views, which iteratively makes the views more agreeable. Extensive experiments on real-world multi-view data sets demonstrate its superiority.},
bibtype = {inproceedings},
author = {Wang, Y. and Wenjie, Z. and Wu, L. and Lin, X. and Fang, M. and Pan, S.},
booktitle = {IJCAI International Joint Conference on Artificial Intelligence}
}
@article{
title = {CogBoost: Boosting for Fast Cost-Sensitive Graph Classification},
type = {article},
year = {2015},
keywords = {Graph classification,boosting,cost-sensitive learning,cutting plane algorithm,large scale graphs,subgraphs},
pages = {2933-2946},
volume = {27},
month = {11},
publisher = {IEEE Computer Society},
day = {1},
id = {89e708b6-304f-37c4-aee6-21dc98184c5f},
created = {2016-04-29T05:47:44.000Z},
accessed = {2016-04-29},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:21.444Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Pan2015a},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
abstract = {Graph classification has drawn great interests in recent years due to the increasing number of applications involving objects with complex structure relationships. To date, all existing graph classification algorithms assume, explicitly or implicitly, that misclassifying instances in different classes incurs an equal amount of cost (or risk), which is often not the case in real-life applications (where misclassifying a certain class of samples, such as diseased patients, is subject to more expensive costs than others). Although cost-sensitive learning has been extensively studied, all methods are based on data with instance-feature representation. Graphs, however, do not have features available for learning and the feature space of graph data is likely infinite and needs to be carefully explored in order to favor classes with a higher cost. In this paper, we propose, CogBoost, a fast cost-sensitive graph classification algorithm, which aims to minimize the misclassification costs (instead of the errors) and achieve fast learning speed for large scale graph data sets. To minimize the misclassification costs, CogBoost iteratively selects the most discriminative subgraph by considering costs of different classes, and then solves a linear programming problem in each iteration by using Bayes decision rule based optimal loss function. In addition, a cutting plane algorithm is derived to speed up the solving of linear programs for fast learning on large scale data sets. Experiments and comparisons on real-world large graph data sets demonstrate the effectiveness and the efficiency of our algorithm.},
bibtype = {article},
author = {Pan, Shirui and Wu, Jia and Zhu, Xingquan},
doi = {10.1109/TKDE.2015.2391115},
journal = {IEEE Transactions on Knowledge and Data Engineering (TKDE)},
number = {11}
}
@article{
title = {Finding the best not the most: Regularized loss minimization subgraph selection for graph classification},
type = {article},
year = {2015},
keywords = {Classification,Feature selection,Graph classification,Sparse learning},
pages = {3783-3796},
volume = {48},
websites = {http://www.scopus.com/inward/record.url?eid=2-s2.0-84937814255&partnerID=tZOtx3y1},
month = {11},
publisher = {Elsevier Ltd},
id = {008b7fd9-ea13-32fd-a3e0-f69da3a49790},
created = {2016-04-29T05:47:45.000Z},
accessed = {2016-04-29},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:17.080Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Pan2015},
folder_uuids = {032bc9cb-8256-40c2-a1d8-d016d563e89a,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
abstract = {Classification on structure data, such as graphs, has drawn wide interest in recent years. Due to the lack of explicit features to represent graphs for training classification models, extensive studies have been focused on extracting the most discriminative subgraphs features from the training graph dataset to transfer graphs into vector data. However, such filter-based methods suffer from two major disadvantages: (1) the subgraph feature selection is separated from the model learning process, so the selected most discriminative subgraphs may not best fit the subsequent learning model, resulting in deteriorated classification results; (2) all these methods rely on users to specify the number of subgraph features K, and suboptimally specified K values often result in significantly reduced classification accuracy. In this paper, we propose a new graph classification paradigm which overcomes the above disadvantages by formulating subgraph feature selection as learning a K-dimensional feature space from an implicit and large subgraph space, with the optimal K value being automatically determined. To achieve the goal, we propose a regularized loss minimization-driven (RLMD) feature selection method for graph classification. RLMD integrates subgraph selection and model learning into a unified framework to find discriminative subgraphs with guaranteed minimum loss w.r.t. the objective function. To automatically determine the optimal number of subgraphs K from the exponentially large subgraph space, an effective elastic net and a subgradient method are proposed to derive the stopping criterion, so that K can be automatically obtained once RLMD converges. The proposed RLMD method enjoys gratifying property including proved convergence and applicability to various loss functions. Experimental results on real-life graph datasets demonstrate significant performance gain.},
bibtype = {article},
author = {Pan, Shirui and Wu, Jia and Zhu, Xingquan and Long, Guodong and Zhang, Chengqi},
doi = {10.1016/j.patcog.2015.05.019},
journal = {Pattern Recognition},
number = {11}
}
@article{
title = {Graph ensemble boosting for imbalanced noisy graph stream classification},
type = {article},
year = {2015},
keywords = {Data streams,graph ensemble boosting (gEBoost),graphs,imbalanced class distributions,noise},
pages = {940-954},
volume = {45},
month = {5},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
id = {72dbe73b-dbc7-37c7-958d-5aa5cf84df90},
created = {2016-04-29T05:47:46.000Z},
accessed = {2016-04-29},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:20.596Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Pan2015c},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
abstract = {Many applications involve stream data with structural dependency, graph representations, and continuously increasing volumes. For these applications, it is very common that their class distributions are imbalanced with minority (or positive) samples being only a small portion of the population, which imposes significant challenges for learning models to accurately identify minority samples. This problem is further complicated with the presence of noise, because they are similar to minority samples and any treatment for the class imbalance may falsely focus on the noise and result in deterioration of accuracy. In this paper, we propose a classification model to tackle imbalanced graph streams with noise. Our method, graph ensemble boosting, employs an ensemble-based framework to partition graph stream into chunks each containing a number of noisy graphs with imbalanced class distributions. For each individual chunk, we propose a boosting algorithm to combine discriminative subgraph pattern selection and model learning as a unified framework for graph classification. To tackle concept drifting in graph streams, an instance level weighting mechanism is used to dynamically adjust the instance weight, through which the boosting framework can emphasize on difficult graph samples. The classifiers built from different graph chunks form an ensemble for graph stream classification. Experiments on real-life imbalanced graph streams demonstrate clear benefits of our boosting design for handling imbalanced noisy graph stream.},
bibtype = {article},
author = {Pan, Shirui and Wu, Jia and Zhu, Xingquan and Zhang, Chengqi},
doi = {10.1109/TCYB.2014.2341031},
journal = {IEEE Transactions on Cybernetics (TCYB)},
number = {5}
}
@article{
title = {Boosting for multi-graph classification},
type = {article},
year = {2015},
keywords = {Boosting,graph classification,multi-graph,multi-instance learning,subgraph mining},
pages = {430-43},
volume = {45},
month = {3},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
id = {ef9cdda8-1807-3ee4-840c-5596cfdac04c},
created = {2016-04-29T05:47:47.000Z},
accessed = {2016-04-29},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:19.238Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Wu2015a},
folder_uuids = {2327f56c-ffc0-4246-bac0-b9fa6098ebfb,a5961aba-0e48-4cf8-9566-d73aaba73d2c},
private_publication = {false},
abstract = {In this paper, we formulate a novel graph-based learning problem, multi-graph classification (MGC), which aims to learn a classifier from a set of labeled bags each containing a number of graphs inside the bag. A bag is labeled positive, if at least one graph in the bag is positive, and negative otherwise. Such a multi-graph representation can be used for many real-world applications, such as webpage classification, where a webpage can be regarded as a bag with texts and images inside the webpage being represented as graphs. This problem is a generalization of multi-instance learning (MIL) but with vital differences, mainly because instances in MIL share a common feature space whereas no feature is available to represent graphs in a multi-graph bag. To solve the problem, we propose a boosting based multi-graph classification framework (bMGC). Given a set of labeled multi-graph bags, bMGC employs dynamic weight adjustment at both bag- and graph-levels to select one subgraph in each iteration as a weak classifier. In each iteration, bag and graph weights are adjusted such that an incorrectly classified bag will receive a higher weight because its predicted bag label conflicts to the genuine label, whereas an incorrectly classified graph will receive a lower weight value if the graph is in a positive bag (or a higher weight if the graph is in a negative bag). Accordingly, bMGC is able to differentiate graphs in positive and negative bags to derive effective classifiers to form a boosting model for MGC. Experiments and comparisons on real-world multi-graph learning tasks demonstrate the algorithm performance.},
bibtype = {article},
author = {Wu, Jia and Pan, Shirui and Zhu, Xingquan and Cai, Zhihua},
doi = {10.1109/TCYB.2014.2327111},
journal = {IEEE Transactions on Cybernetics (TCYB)},
number = {3}
}
@inproceedings{
title = {Multi-graph-view learning for complicated object classification},
type = {inproceedings},
year = {2015},
pages = {3953-3959 (CORE Ranked A*)},
volume = {2015-Janua},
publisher = {International Joint Conferences on Artificial Intelligence},
id = {5e9269c6-d5a7-3858-ad2a-ca9c2c05bed8},
created = {2016-04-29T05:47:48.000Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2022-04-10T12:11:22.332Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Wu2015c},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d,2327f56c-ffc0-4246-bac0-b9fa6098ebfb},
private_publication = {false},
abstract = {In this paper, we propose to represent and classify complicated objects. In order to represent the objects, we propose a multi-graph-view model which uses graphs constructed from multiple graph-views to represent an object. In addition, a bag based multi-graph model is further used to relax labeling by only requiring one label for a bag of graphs, which represent one object. In order to learn classification models, we propose a multi-graph-view bag learning algorithm (MGVBL), which aims to explore subgraph features from multiple graphviews for learning. By enabling a joint regularization across multiple graph-views, and enforcing labeling constraints at the bag and graph levels, MGVBL is able to discover most effective subgraph features across all graph-views for learning. Experiments on real-world learning tasks demonstrate the performance of MGVBL for complicated object classification.},
bibtype = {inproceedings},
author = {Wu, Jia and Pan, Shirui and Zhu, Xingquan and Cai, Zhihua and Zhang, Chengqi},
booktitle = {IJCAI International Joint Conference on Artificial Intelligence}
}
@inproceedings{
title = {Multi-Graph-View Learning for Graph Classification},
type = {inproceedings},
year = {2014},
pages = {590-599},
id = {3a3bd5bd-bb67-397c-9607-3ba3fffbff16},
created = {2015-04-01T10:49:04.000Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2021-06-15T12:46:22.796Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {jiaICDM2014},
source_type = {inproceedings},
folder_uuids = {bc12cb20-e8d1-4699-9ef7-5e5c8da46164,f3b8cf54-f818-49eb-a899-33ac83c5e58d},
private_publication = {false},
bibtype = {inproceedings},
author = {Wu, Jia and Hong, Zhibin and Pan, Shirui and Zhu, Xingquan and Zhang, Chengqi},
booktitle = {International Conference on Data Mining}
}
@inproceedings{
title = {Graph classification with imbalanced class distributions and noise},
type = {inproceedings},
year = {2013},
keywords = {Machine Learning},
pages = {1586-1592},
id = {1907f272-b130-35ef-9e88-8f92cd3c9bb6},
created = {2014-12-16T23:49:26.000Z},
accessed = {2014-12-16},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2021-06-25T11:52:05.393Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {false},
hidden = {false},
citation_key = {Pan2013},
folder_uuids = {f3b8cf54-f818-49eb-a899-33ac83c5e58d},
private_publication = {false},
abstract = {Recent years have witnessed an increasing number of applications involving data with structural dependency and graph representations. For these applications, it is very common that their class distribution is imbalanced with minority samples being only a small portion of the population. Such imbalanced class distributions impose significant challenges to the learning algorithms. This problem is further complicated with the presence of noise or outliers in the graph data. In this paper, we propose an imbalanced graph boosting algorithm, igBoost, that progressively selects informative subgraph patterns from imbalanced graph data for learning. To handle class imbalance, we take class distributions into consideration to assign different weight values to graphs. The distance of each graph to its class center is also considered to adjust the weight to reduce the impact of noisy graph data. The weight values are integrated into the iterative subgraph feature selection and margin learning process to achieve maximum benefits. Experiments on realworld graph data with different degrees of class imbalance and noise demonstrate the algorithm performance.},
bibtype = {inproceedings},
author = {Pan, Shirui and Zhu, Xingquan},
booktitle = {IJCAI International Joint Conference on Artificial Intelligence}
}
@inproceedings{
title = {Graph stream classification using labeled and unlabeled graphs},
type = {inproceedings},
year = {2013},
pages = {398-409},
institution = {IEEE},
id = {27dff4ed-a178-38c4-92bc-e475dbc2c331},
created = {2015-04-01T10:49:07.000Z},
file_attached = {false},
profile_id = {079852a8-52df-3ac8-a41c-8bebd97d6b2b},
last_modified = {2021-06-15T12:46:24.310Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Pan2013ICDE},
source_type = {inproceedings},
folder_uuids = {bc12cb20-e8d1-4699-9ef7-5e5c8da46164,f3b8cf54-f818-49eb-a899-33ac83c5e58d},
private_publication = {false},
abstract = {Graph classification is becoming increasingly popular due to the rapidly rising applications involving data with structural dependency. The wide spread of the graph applications and the inherent complex relationships between graph objects have made the labels of the graph data expensive and/or difficult to obtain, especially for applications involving dynamic changing graph records. While labeled graphs are limited, the copious amounts of unlabeled graphs are often easy to obtain with trivial efforts. In this paper, we propose a framework to build a stream based graph classification model by combining both labeled and unlabeled graphs. Our method, called gSLU, employs an ensemble based framework to partition graph streams into a number of graph chunks each containing some labeled and unlabeled graphs. For each individual chunk, we propose a minimum-redundancy subgraph feature selection module to select a set of informative subgraph features to build a classifier. To tackle the concept drifting in graph streams, an instance level weighting mechanism is used to dynamically adjust the instance weight, through which the subgraph feature selection can emphasize on difficult graph samples. The classifiers built from different graph chunks form an ensemble for graph stream classification. Experiments on real-world graph streams demonstrate clear benefits of using minimum-redundancy subgraph features to build accurate classifiers. By employing instance level weighting, our graph ensemble model can effectively adapt to the concept drifting in the graph stream for classification. © 2013 IEEE.},
bibtype = {inproceedings},
author = {Pan, Shirui and Zhu, Xingquan and Zhang, Chengqi and Yu, Philip S.},
doi = {10.1109/ICDE.2013.6544842},
booktitle = {Proceedings - International Conference on Data Engineering}
}