\n \n \n
\n
\n\n \n \n \n \n \n Reinforced, incremental and cross-lingual event detection from social messages.\n \n \n \n\n\n \n Peng, H.; Zhang, R.; Li, S.; Cao, Y.; Pan, S.; and Philip, S Y.\n\n\n \n\n\n\n
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 45(1): 980–998. 2022.\n
Publisher: IEEE\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{peng_reinforced_2022,\n\ttitle = {Reinforced, incremental and cross-lingual event detection from social messages},\n\tvolume = {45},\n\tcopyright = {All rights reserved},\n\tnumber = {1},\n\tjournal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},\n\tauthor = {Peng, Hao and Zhang, Ruitong and Li, Shaoning and Cao, Yuwei and Pan, Shirui and Philip, S Yu},\n\tyear = {2022},\n\tnote = {Publisher: IEEE},\n\tpages = {980--998},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Neural Temporal Walks: Motif-Aware Representation Learning on Continuous-Time Dynamic Graphs.\n \n \n \n\n\n \n Jin, M.; Li, Y.; and Pan, S.\n\n\n \n\n\n\n In
Advances in Neural Information Processing Systems, NeurIPS-22, 2022. Advances in Neural Information Processing Systems, NeurIPS-22\n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{jin_neural_2022,\n\ttitle = {Neural {Temporal} {Walks}: {Motif}-{Aware} {Representation} {Learning} on {Continuous}-{Time} {Dynamic} {Graphs}},\n\tcopyright = {All rights reserved},\n\tbooktitle = {Advances in {Neural} {Information} {Processing} {Systems}, {NeurIPS}-22},\n\tpublisher = {Advances in Neural Information Processing Systems, NeurIPS-22},\n\tauthor = {Jin, Ming and Li, Yuan-Fang and Pan, Shirui},\n\tyear = {2022},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Multi-relational graph neural architecture search with fine-grained message passing.\n \n \n \n\n\n \n Zheng, X.; Zhang, M.; Chen, C.; Li, C.; Zhou, C.; and Pan, S.\n\n\n \n\n\n\n In
2022 IEEE International Conference on Data Mining (ICDM), pages 783–792, 2022. IEEE\n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{zheng_multi-relational_2022,\n\ttitle = {Multi-relational graph neural architecture search with fine-grained message passing},\n\tcopyright = {All rights reserved},\n\tbooktitle = {2022 {IEEE} {International} {Conference} on {Data} {Mining} ({ICDM})},\n\tpublisher = {IEEE},\n\tauthor = {Zheng, Xin and Zhang, Miao and Chen, Chunyang and Li, Chaojie and Zhou, Chuan and Pan, Shirui},\n\tyear = {2022},\n\tpages = {783--792},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n A Dynamic Variational Framework for Open-World Node Classification in Structured Sequences.\n \n \n \n\n\n \n Zhang, Q.; Li, Q.; Chen, X.; Zhang, P.; Pan, S.; Fournier-Viger, P.; and Huang, J. Z.\n\n\n \n\n\n\n In
IEEE International Conference on Data Mining (ICDM), 2022. \n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{zhang_dynamic_2022,\n\ttitle = {A {Dynamic} {Variational} {Framework} for {Open}-{World} {Node} {Classification} in {Structured} {Sequences}},\n\tcopyright = {All rights reserved},\n\tbooktitle = {{IEEE} {International} {Conference} on {Data} {Mining} ({ICDM})},\n\tauthor = {Zhang, Qin and Li, Qincai and Chen, Xiaojun and Zhang, Peng and Pan, Shirui and Fournier-Viger, Philippe and Huang, Joshua Zhexue},\n\tyear = {2022},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n How Far are We from Robust Long Abstractive Summarization?.\n \n \n \n\n\n \n Koh, H. Y.; Ju, J.; Zhang, H.; Liu, M.; and Pan, S.\n\n\n \n\n\n\n In
2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022. \n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{koh_how_2022,\n\ttitle = {How {Far} are {We} from {Robust} {Long} {Abstractive} {Summarization}?},\n\tcopyright = {All rights reserved},\n\tbooktitle = {2022 {Conference} on {Empirical} {Methods} in {Natural} {Language} {Processing} ({EMNLP})},\n\tauthor = {Koh, Huan Yee and Ju, Jiaxin and Zhang, He and Liu, Ming and Pan, Shirui},\n\tyear = {2022},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Unifying Graph Contrastive Learning with Flexible Contextual Scopes.\n \n \n \n\n\n \n Zheng, Y.; Zheng, Y.; Zhou, X.; Gong, C.; Lee, V.; and Pan, S.\n\n\n \n\n\n\n In
IEEE International Conference on Data Mining (ICDM), 2022. \n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{zheng_unifying_2022,\n\ttitle = {Unifying {Graph} {Contrastive} {Learning} with {Flexible} {Contextual} {Scopes}},\n\tcopyright = {All rights reserved},\n\tbooktitle = {{IEEE} {International} {Conference} on {Data} {Mining} ({ICDM})},\n\tauthor = {Zheng, Yizhen and Zheng, Yu and Zhou, Xiaofei and Gong, Chen and Lee, Vincent and Pan, Shirui},\n\tyear = {2022},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n \n\n\n
\n
\n\n \n \n \n \n \n Towards spatio-temporal aware traffic time series forecasting.\n \n \n \n\n\n \n Cirstea, R.; Yang, B.; Guo, C.; Kieu, T.; and Pan, S.\n\n\n \n\n\n\n In
2022 IEEE 38th International Conference on Data Engineering (ICDE), pages 2900–2913, 2022. IEEE\n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{cirstea_towards_2022,\n\ttitle = {Towards spatio-temporal aware traffic time series forecasting},\n\tcopyright = {All rights reserved},\n\tbooktitle = {2022 {IEEE} 38th {International} {Conference} on {Data} {Engineering} ({ICDE})},\n\tpublisher = {IEEE},\n\tauthor = {Cirstea, Razvan-Gabriel and Yang, Bin and Guo, Chenjuan and Kieu, Tung and Pan, Shirui},\n\tyear = {2022},\n\tpages = {2900--2913},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n A Probabilistic Graphical Model Based on Neural-Symbolic Reasoning for Visual Relationship Detection.\n \n \n \n\n\n \n Yu, D.; Yang, B.; Wei, Q.; Li, A.; and Pan, S.\n\n\n \n\n\n\n In
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR-22), pages 10609–10618, 2022. \n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{yu_probabilistic_2022,\n\ttitle = {A {Probabilistic} {Graphical} {Model} {Based} on {Neural}-{Symbolic} {Reasoning} for {Visual} {Relationship} {Detection}},\n\tcopyright = {All rights reserved},\n\tbooktitle = {{IEEE}/{CVF} {Conference} on {Computer} {Vision} and {Pattern} {Recognition} ({CVPR}-22)},\n\tauthor = {Yu, Dongran and Yang, Bo and Wei, Qianhao and Li, Anchen and Pan, Shirui},\n\tyear = {2022},\n\tpages = {10609--10618},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Ultrahyperbolic Knowledge Graph Embeddings.\n \n \n \n\n\n \n Xiong, B.; Zhu, S.; Nayyeri, M.; Xu, C.; Pan, S.; Zhou, C.; and Staab, S.\n\n\n \n\n\n\n In
ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD-22, 2022. \n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{xiong_ultrahyperbolic_2022,\n\ttitle = {Ultrahyperbolic {Knowledge} {Graph} {Embeddings}},\n\tcopyright = {All rights reserved},\n\tbooktitle = {{ACM} {SIGKDD} {Conference} on {Knowledge} {Discovery} and {Data} {Mining}, {KDD}-22},\n\tauthor = {Xiong, Bo and Zhu, Shichao and Nayyeri, Mojtaba and Xu, Chengjin and Pan, Shirui and Zhou, Chuan and Staab, Steffen},\n\tyear = {2022},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics.\n \n \n \n\n\n \n Koh, H. Y.; Ju, J.; Liu, M.; and Pan, S.\n\n\n \n\n\n\n
ACM Computing Surveys (CSUR). 2022.\n
Publisher: ACM\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{koh_empirical_2022,\n\ttitle = {An {Empirical} {Survey} on {Long} {Document} {Summarization}: {Datasets}, {Models} and {Metrics}},\n\tcopyright = {All rights reserved},\n\tjournal = {ACM Computing Surveys (CSUR)},\n\tauthor = {Koh, Huan Yee and Ju, Jiaxin and Liu, Ming and Pan, Shirui},\n\tyear = {2022},\n\tnote = {Publisher: ACM},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discrimination.\n \n \n \n\n\n \n Zheng, Y.; Pan, S.; Lee, V. C.; Zheng, Y.; and Yu, P. S\n\n\n \n\n\n\n In
Advances in Neural Information Processing Systems, NeurIPS-22, 2022. \n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{zheng_rethinking_2022,\n\ttitle = {Rethinking and {Scaling} {Up} {Graph} {Contrastive} {Learning}: {An} {Extremely} {Efficient} {Approach} with {Group} {Discrimination}},\n\tcopyright = {All rights reserved},\n\tbooktitle = {Advances in {Neural} {Information} {Processing} {Systems}, {NeurIPS}-22},\n\tauthor = {Zheng, Yizhen and Pan, Shirui and Lee, Vincent Cs and Zheng, Yu and Yu, Philip S},\n\tyear = {2022},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Task Scheduling in Three-Dimensional Spatial Crowdsourcing: A Social Welfare Perspective.\n \n \n \n\n\n \n Wang, L.; Yang, D.; Yu, Z.; Xiong, F.; Han, L.; Pan, S.; and Guo, B.\n\n\n \n\n\n\n
IEEE Transactions on Mobile Computing. 2022.\n
Publisher: IEEE\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{wang_task_2022,\n\ttitle = {Task {Scheduling} in {Three}-{Dimensional} {Spatial} {Crowdsourcing}: {A} {Social} {Welfare} {Perspective}},\n\tcopyright = {All rights reserved},\n\tjournal = {IEEE Transactions on Mobile Computing},\n\tauthor = {Wang, Liang and Yang, Dingqi and Yu, Zhiwen and Xiong, Fei and Han, Lei and Pan, Shirui and Guo, Bin},\n\tyear = {2022},\n\tnote = {Publisher: IEEE},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Fire Burns, Sword Cuts: Commonsense Inductive Bias for Exploration in Text-based Games.\n \n \n \n\n\n \n Ryu, D.; Shareghi, E.; Fang, M.; Xu, Y.; Pan, S.; and Haf, R.\n\n\n \n\n\n\n In
Annual Meeting of the Association for Computational Linguistics (ACL), volume 2, pages 515–522, 2022. \n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{ryu_fire_2022,\n\ttitle = {Fire {Burns}, {Sword} {Cuts}: {Commonsense} {Inductive} {Bias} for {Exploration} in {Text}-based {Games}},\n\tvolume = {2},\n\tcopyright = {All rights reserved},\n\tbooktitle = {Annual {Meeting} of the {Association} for {Computational} {Linguistics} ({ACL})},\n\tauthor = {Ryu, Dongwon and Shareghi, Ehsan and Fang, Meng and Xu, Yunqiu and Pan, Shirui and Haf, Reza},\n\tyear = {2022},\n\tpages = {515--522},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n CGMN: A Contrastive Graph Matching Network for Self-Supervised Graph Similarity Learning.\n \n \n \n\n\n \n Jin, D.; Wang, L.; Zheng, Y.; Li, X.; Jiang, F.; Lin, W.; and Pan, S.\n\n\n \n\n\n\n In
International Joint Conference on Artificial Intelligence, IJCAI 2022, 2022. \n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{jin_cgmn:_2022,\n\ttitle = {{CGMN}: {A} {Contrastive} {Graph} {Matching} {Network} for {Self}-{Supervised} {Graph} {Similarity} {Learning}},\n\tcopyright = {All rights reserved},\n\tbooktitle = {International {Joint} {Conference} on {Artificial} {Intelligence}, {IJCAI} 2022},\n\tauthor = {Jin, Di and Wang, Luzhi and Zheng, Yizhen and Li, Xiang and Jiang, Fei and Lin, Wei and Pan, Shirui},\n\tyear = {2022},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Cyclic transfer learning for recommender systems with heterogeneous feedbacks.\n \n \n \n\n\n \n Ni, X.; Xiong, F.; Hu, Y.; Pan, S.; Chen, H.; and Wang, L.\n\n\n \n\n\n\n In
Proceedings of the 2022 SIAM International Conference on Data Mining (SDM), pages 567–575, 2022. Society for Industrial and Applied Mathematics\n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{ni_cyclic_2022,\n\ttitle = {Cyclic transfer learning for recommender systems with heterogeneous feedbacks},\n\tcopyright = {All rights reserved},\n\tbooktitle = {Proceedings of the 2022 {SIAM} {International} {Conference} on {Data} {Mining} ({SDM})},\n\tpublisher = {Society for Industrial and Applied Mathematics},\n\tauthor = {Ni, Xuelian and Xiong, Fei and Hu, Yutian and Pan, Shirui and Chen, Hongshu and Wang, Liang},\n\tyear = {2022},\n\tpages = {567--575},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Fine-grained attributed graph clustering.\n \n \n \n\n\n \n Kang, Z.; Liu, Z.; Pan, S.; and Tian, L.\n\n\n \n\n\n\n In
Proceedings of the 2022 SIAM International Conference on Data Mining (SDM), pages 370–378, 2022. Society for Industrial and Applied Mathematics\n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{kang_fine-grained_2022,\n\ttitle = {Fine-grained attributed graph clustering},\n\tcopyright = {All rights reserved},\n\tbooktitle = {Proceedings of the 2022 {SIAM} {International} {Conference} on {Data} {Mining} ({SDM})},\n\tpublisher = {Society for Industrial and Applied Mathematics},\n\tauthor = {Kang, Zhao and Liu, Zhanyu and Pan, Shirui and Tian, Ling},\n\tyear = {2022},\n\tpages = {370--378},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Exploring Relational Semantics for Inductive Knowledge Graph Completion.\n \n \n \n\n\n \n Wang, C.; Zhou, X.; Pan, S.; Dong, L.; Song, Z.; and Sha, Y.\n\n\n \n\n\n\n In
AAAI Conference on Artificial Intelligence, AAAI-22, 2022. \n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{wang_exploring_2022,\n\ttitle = {Exploring {Relational} {Semantics} for {Inductive} {Knowledge} {Graph} {Completion}},\n\tcopyright = {All rights reserved},\n\tbooktitle = {{AAAI} {Conference} on {Artificial} {Intelligence}, {AAAI}-22},\n\tauthor = {Wang, Changjian and Zhou, Xiaofei and Pan, Shirui and Dong, Linhua and Song, Zeliang and Sha, Ying},\n\tyear = {2022},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Attraction and repulsion: Unsupervised domain adaptive graph contrastive learning network.\n \n \n \n\n\n \n Wu, M.; Pan, S.; and Zhu, X.\n\n\n \n\n\n\n
IEEE Transactions on Emerging Topics in Computational Intelligence, 6(5): 1079–1091. 2022.\n
Publisher: IEEE\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{wu_attraction_2022,\n\ttitle = {Attraction and repulsion: {Unsupervised} domain adaptive graph contrastive learning network},\n\tvolume = {6},\n\tcopyright = {All rights reserved},\n\tnumber = {5},\n\tjournal = {IEEE Transactions on Emerging Topics in Computational Intelligence},\n\tauthor = {Wu, Man and Pan, Shirui and Zhu, Xingquan},\n\tyear = {2022},\n\tnote = {Publisher: IEEE},\n\tpages = {1079--1091},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Survey on Graph Neural Network Acceleration: An Algorithmic Perspective.\n \n \n \n\n\n \n Liu, X.; Yan, M.; Deng, L.; Li, G.; Ye, X.; Fan, D.; Pan, S.; and Xie, Y.\n\n\n \n\n\n\n In
International Joint Conference on Artificial Intelligence, IJCAI 2022, 2022. \n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{liu_survey_2022,\n\ttitle = {Survey on {Graph} {Neural} {Network} {Acceleration}: {An} {Algorithmic} {Perspective}},\n\tcopyright = {All rights reserved},\n\tbooktitle = {International {Joint} {Conference} on {Artificial} {Intelligence}, {IJCAI} 2022},\n\tauthor = {Liu, Xin and Yan, Mingyu and Deng, Lei and Li, Guoqi and Ye, Xiaochun and Fan, Dongrui and Pan, Shirui and Xie, Yuan},\n\tyear = {2022},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Projective Ranking-based GNN Evasion Attacks.\n \n \n \n\n\n \n Zhang, H.; Yuan, X.; Zhou, C.; and Pan, S.\n\n\n \n\n\n\n
IEEE Transactions on Knowledge and Data Engineering (TKDE). 2022.\n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{zhang_projective_2022,\n\ttitle = {Projective {Ranking}-based {GNN} {Evasion} {Attacks}},\n\tcopyright = {All rights reserved},\n\tjournal = {IEEE Transactions on Knowledge and Data Engineering (TKDE)},\n\tauthor = {Zhang, He and Yuan, Xingliang and Zhou, Chuan and Pan, Shirui},\n\tyear = {2022},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs.\n \n \n \n\n\n \n Jin, M.; Zheng, Y.; Li, Y.; Chen, S.; Yang, B.; and Pan, S.\n\n\n \n\n\n\n
IEEE Transactions on Knowledge and Data Engineering (TKDE). 2022.\n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{jin_multivariate_2022,\n\ttitle = {Multivariate {Time} {Series} {Forecasting} with {Dynamic} {Graph} {Neural} {ODEs}},\n\tcopyright = {All rights reserved},\n\tjournal = {IEEE Transactions on Knowledge and Data Engineering (TKDE)},\n\tauthor = {Jin, Ming and Zheng, Yu and Li, Yuan-Fang and Chen, Siheng and Yang, Bin and Pan, Shirui},\n\tyear = {2022},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Predicting Human Mobility via Graph Convolutional Dual-attentive Networks.\n \n \n \n\n\n \n Dang, W.; Wang, H.; Pan, S.; Zhang, P.; Zhou, C.; Chen, X.; and Wang, J.\n\n\n \n\n\n\n In
ACM International Conference on Web Search and Data Mining (WSDM), pages 192–200, 2022. \n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{dang_predicting_2022,\n\ttitle = {Predicting {Human} {Mobility} via {Graph} {Convolutional} {Dual}-attentive {Networks}},\n\tcopyright = {All rights reserved},\n\tbooktitle = {{ACM} {International} {Conference} on {Web} {Search} and {Data} {Mining} ({WSDM})},\n\tauthor = {Dang, Weizhen and Wang, Haibo and Pan, Shirui and Zhang, Pei and Zhou, Chuan and Chen, Xin and Wang, Jilong},\n\tyear = {2022},\n\tpages = {192--200},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Dual Space Graph Contrastive Learning.\n \n \n \n\n\n \n Yang, H.; Chen, H.; Pan, S.; Li, L.; Yu, P. S; and Xu, G.\n\n\n \n\n\n\n In
The Web Conference (WWW-2022), 2022. \n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{yang_dual_2022,\n\ttitle = {Dual {Space} {Graph} {Contrastive} {Learning}},\n\tcopyright = {All rights reserved},\n\tbooktitle = {The {Web} {Conference} ({WWW}-2022)},\n\tauthor = {Yang, Haoran and Chen, Hongxu and Pan, Shirui and Li, Lin and Yu, Philip S and Xu, Guandong},\n\tyear = {2022},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Towards Unsupervised Deep Graph Structure Learning.\n \n \n \n\n\n \n Liu, Y.; Zheng, Y.; Zhang, D.; Chen, H.; Peng, H.; and Pan, S.\n\n\n \n\n\n\n In
The Web Conference (WWW-2022), 2022. \n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{liu_towards_2022,\n\ttitle = {Towards {Unsupervised} {Deep} {Graph} {Structure} {Learning}},\n\tcopyright = {All rights reserved},\n\tbooktitle = {The {Web} {Conference} ({WWW}-2022)},\n\tauthor = {Liu, Yixin and Zheng, Yu and Zhang, Daokun and Chen, Hongxu and Peng, Hao and Pan, Shirui},\n\tyear = {2022},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule.\n \n \n \n\n\n \n Zhang, M.; Hu, J.; Su, S.; Pan, S.; Chang, X.; Yang, B.; and Haffari, G.\n\n\n \n\n\n\n In
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR-22), 2022. \n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{zhang_balenas:_2022,\n\ttitle = {{BaLeNAS}: {Differentiable} {Architecture} {Search} via the {Bayesian} {Learning} {Rule}},\n\tcopyright = {All rights reserved},\n\tbooktitle = {{IEEE}/{CVF} {Conference} on {Computer} {Vision} and {Pattern} {Recognition} ({CVPR}-22)},\n\tauthor = {Zhang, Miao and Hu, Jilin and Su, Steven and Pan, Shirui and Chang, Xiaojun and Yang, Bin and Haffari, Gholamreza},\n\tyear = {2022},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Multi-Graph Fusion Networks for Urban Region Embedding.\n \n \n \n\n\n \n Wu, S.; Yan, X.; Fan, X.; Pan, S.; Zhu, S.; Zheng, C.; Cheng, M.; and Wang, C.\n\n\n \n\n\n\n In
International Joint Conference on Artificial Intelligence, IJCAI 2022, 2022. \n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{wu_multi-graph_2022,\n\ttitle = {Multi-{Graph} {Fusion} {Networks} for {Urban} {Region} {Embedding}},\n\tcopyright = {All rights reserved},\n\tbooktitle = {International {Joint} {Conference} on {Artificial} {Intelligence}, {IJCAI} 2022},\n\tauthor = {Wu, Shangbin and Yan, Xu and Fan, Xiaoliang and Pan, Shirui and Zhu, Shichao and Zheng, Chuanpan and Cheng, Ming and Wang, Cheng},\n\tyear = {2022},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n TraverseNet: Unifying Space and Time in Message Passing for Traffic Forecasting.\n \n \n \n\n\n \n Wu, Z.; Zheng, D.; Pan, S.; Gan, Q.; Long, G.; and Karypis, G.\n\n\n \n\n\n\n
IEEE Transactions on Neural Networks and Learning Systems (TNNLS). 2022.\n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{wu_traversenet:_2022,\n\ttitle = {{TraverseNet}: {Unifying} {Space} and {Time} in {Message} {Passing} for {Traffic} {Forecasting}},\n\tcopyright = {All rights reserved},\n\tjournal = {IEEE Transactions on Neural Networks and Learning Systems (TNNLS)},\n\tauthor = {Wu, Zonghan and Zheng, Da and Pan, Shirui and Gan, Quan and Long, Guodong and Karypis, George},\n\tyear = {2022},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Beyond low-pass filtering: Graph convolutional networks with automatic filtering.\n \n \n \n\n\n \n Wu, Z.; Pan, S.; Long, G.; Jiang, J.; and Zhang, C.\n\n\n \n\n\n\n
IEEE Transactions on Knowledge and Data Engineering (TKDE). 2022.\n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{wu_beyond_2022,\n\ttitle = {Beyond low-pass filtering: {Graph} convolutional networks with automatic filtering},\n\tcopyright = {All rights reserved},\n\tjournal = {IEEE Transactions on Knowledge and Data Engineering (TKDE)},\n\tauthor = {Wu, Zonghan and Pan, Shirui and Long, Guodong and Jiang, Jing and Zhang, Chengqi},\n\tyear = {2022},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Graph self-supervised learning: A survey.\n \n \n \n\n\n \n Liu, Y.; Jin, M.; Pan, S.; Zhou, C.; Zheng, Y.; Xia, F.; and Yu, P. S\n\n\n \n\n\n\n
IEEE Transactions on Knowledge and Data Engineering (TKDE). 2022.\n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{liu_graph_2022,\n\ttitle = {Graph self-supervised learning: {A} survey},\n\tcopyright = {All rights reserved},\n\tjournal = {IEEE Transactions on Knowledge and Data Engineering (TKDE)},\n\tauthor = {Liu, Yixin and Jin, Ming and Pan, Shirui and Zhou, Chuan and Zheng, Yu and Xia, Feng and Yu, Philip S},\n\tyear = {2022},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Model Extraction Attacks on Graph Neural Networks: Taxonomy and Realization.\n \n \n \n\n\n \n Wu, B.; Yang, X.; Pan, S.; and Yuan, X.\n\n\n \n\n\n\n In
ACM ASIA Conference on Computer and Communications Security (ACM ASIACCS 2022), 2022. \n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{wu_model_2022,\n\ttitle = {Model {Extraction} {Attacks} on {Graph} {Neural} {Networks}: {Taxonomy} and {Realization}},\n\tcopyright = {All rights reserved},\n\tbooktitle = {{ACM} {ASIA} {Conference} on {Computer} and {Communications} {Security} ({ACM} {ASIACCS} 2022)},\n\tauthor = {Wu, Bang and Yang, Xiangwen and Pan, Shirui and Yuan, Xingliang},\n\tyear = {2022},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Learning multi-level weight-centric features for few-shot learning.\n \n \n \n\n\n \n Liang, M.; Huang, S.; Pan, S.; Gong, M.; and Liu, W.\n\n\n \n\n\n\n
Pattern Recognition (PR), 128: 108662. 2022.\n
\n\n
\n\n
\n\n
\n\n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{liang_learning_2022,\n\ttitle = {Learning multi-level weight-centric features for few-shot learning},\n\tvolume = {128},\n\tcopyright = {All rights reserved},\n\tissn = {0031-3203},\n\tdoi = {https://doi.org/10.1016/j.patcog.2022.108662},\n\tabstract = {Few-shot learning is currently enjoying a considerable resurgence of interest, aided by the recent advance of deep learning. Contemporary approaches based on weight-generation scheme delivers a straightforward and flexible solution to the problem. However, they did not fully consider both the representation power for unseen categories and weight generation capacity in feature learning, making it a significant performance bottleneck. This paper proposes a multi-level weight-centric feature learning to give full play to feature extractor’s dual roles in few-shot learning. Our proposed method consists of two essential techniques: a weight-centric training strategy to improve the features’ prototype-ability and a multi-level feature incorporating a mid- and relation-level information. The former increases the feasibility of constructing a discriminative decision boundary based on a few samples. Simultaneously, the latter helps improve the transferability for characterizing novel classes and preserve classification capability for base classes. We extensively evaluate our approach to low-shot classification benchmarks. Experiments demonstrate our proposed method significantly outperforms its counterparts in both standard and generalized settings and using different network backbones.},\n\tjournal = {Pattern Recognition (PR)},\n\tauthor = {Liang, Mingjiang and Huang, Shaoli and Pan, Shirui and Gong, Mingming and Liu, Wei},\n\tyear = {2022},\n\tpages = {108662},\n}\n\n\n\n
\n
\n\n\n
\n Few-shot learning is currently enjoying a considerable resurgence of interest, aided by the recent advance of deep learning. Contemporary approaches based on weight-generation scheme delivers a straightforward and flexible solution to the problem. However, they did not fully consider both the representation power for unseen categories and weight generation capacity in feature learning, making it a significant performance bottleneck. This paper proposes a multi-level weight-centric feature learning to give full play to feature extractor’s dual roles in few-shot learning. Our proposed method consists of two essential techniques: a weight-centric training strategy to improve the features’ prototype-ability and a multi-level feature incorporating a mid- and relation-level information. The former increases the feasibility of constructing a discriminative decision boundary based on a few samples. Simultaneously, the latter helps improve the transferability for characterizing novel classes and preserve classification capability for base classes. We extensively evaluate our approach to low-shot classification benchmarks. Experiments demonstrate our proposed method significantly outperforms its counterparts in both standard and generalized settings and using different network backbones.\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Deep neighbor-aware embedding for node clustering in attributed graphs.\n \n \n \n\n\n \n Wang, C.; Pan, S.; Yu, C. P.; Hu, R.; Long, G.; and Zhang, C.\n\n\n \n\n\n\n
Pattern Recognition (PR), 122: 108230. 2022.\n
\n\n
\n\n
\n\n
\n\n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{wang_deep_2022,\n\ttitle = {Deep neighbor-aware embedding for node clustering in attributed graphs},\n\tvolume = {122},\n\tcopyright = {All rights reserved},\n\tissn = {0031-3203},\n\tdoi = {https://doi.org/10.1016/j.patcog.2021.108230},\n\tabstract = {Node clustering aims to partition the vertices in a graph into multiple groups or communities. Existing studies have mostly focused on developing deep learning approaches to learn a latent representation of nodes, based on which simple clustering methods like k-means are applied. These two-step frameworks for node clustering 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 clustering-directed deep learning approach, Deep Neighbor-aware Embedded Node Clustering (DNENC for short) for clustering graph data. Our method focuses on attributed graphs to sufficiently explore the two sides of information in graphs. It encodes the topological structure and node content in a graph into a compact representation via a neighbor-aware graph autoencoder, which progressively absorbs information from neighbors via a convolutional or attentional encoder. Multiple neighbor-aware encoders are stacked to build a deep architecture followed by an inner-product decoder for reconstructing the graph structure. Furthermore, soft labels are generated to supervise a self-training process, which iteratively refines the node clustering results. The self-training process is jointly learned and optimized with the graph embedding in a unified framework, to benefit both components mutually. Experimental results compared with state-of-the-art algorithms demonstrate the good performance of our framework.},\n\tjournal = {Pattern Recognition (PR)},\n\tauthor = {Wang, Chun and Pan, Shirui and Yu, Celina P. and Hu, Ruiqi and Long, Guodong and Zhang, Chengqi},\n\tyear = {2022},\n\tpages = {108230},\n}\n\n\n\n
\n
\n\n\n
\n Node clustering aims to partition the vertices in a graph into multiple groups or communities. Existing studies have mostly focused on developing deep learning approaches to learn a latent representation of nodes, based on which simple clustering methods like k-means are applied. These two-step frameworks for node clustering 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 clustering-directed deep learning approach, Deep Neighbor-aware Embedded Node Clustering (DNENC for short) for clustering graph data. Our method focuses on attributed graphs to sufficiently explore the two sides of information in graphs. It encodes the topological structure and node content in a graph into a compact representation via a neighbor-aware graph autoencoder, which progressively absorbs information from neighbors via a convolutional or attentional encoder. Multiple neighbor-aware encoders are stacked to build a deep architecture followed by an inner-product decoder for reconstructing the graph structure. Furthermore, soft labels are generated to supervise a self-training process, which iteratively refines the node clustering results. The self-training process is jointly learned and optimized with the graph embedding in a unified framework, to benefit both components mutually. Experimental results compared with state-of-the-art algorithms demonstrate the good performance of our framework.\n
\n\n\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n A Probabilistic Graphical Model Based on Neural-symbolic Reasoning for Visual Relationship Detection.\n \n \n \n\n\n \n Yu, D.; Yang, B.; Wei, Q.; Li, A.; and Pan, S.\n\n\n \n\n\n\n In
IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR-22, New Orleans, Louisiana, US, Jun 19-24, 2022, pages 10599–10608, 2022. \n
\n\n
\n\n
\n\n
\n\n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{yu_probabilistic_2022,\n\ttitle = {A {Probabilistic} {Graphical} {Model} {Based} on {Neural}-symbolic {Reasoning} for {Visual} {Relationship} {Detection}},\n\tcopyright = {All rights reserved},\n\tdoi = {10.1109/CVPR52688.2022.01035 (CORE Ranked A*)},\n\tbooktitle = {{IEEE}/{CVF} {Conference} on {Computer} {Vision} and {Pattern} {Recognition}, {CVPR}-22, {New} {Orleans}, {Louisiana}, {US}, {Jun} 19-24, 2022},\n\tauthor = {Yu, Dongran and Yang, Bo and Wei, Qianhao and Li, Anchen and Pan, Shirui},\n\tyear = {2022},\n\tpages = {10599--10608},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n BaLeNAS: Differentiable Architecture Search via Bayesian Learning Rule.\n \n \n \n\n\n \n Zhang, M.; Pan, S.; Chang, X.; Su, S.; Hu, J.; Haffari, R.; and Yang, B.\n\n\n \n\n\n\n In
IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR-22, New Orleans, Louisiana, US, Jun 19-24, 2022, pages 11861–11870, 2022. \n
\n\n
\n\n
\n\n
\n\n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{zhang_balenas:_2022,\n\ttitle = {{BaLeNAS}: {Differentiable} {Architecture} {Search} via {Bayesian} {Learning} {Rule}},\n\tcopyright = {All rights reserved},\n\tdoi = {10.1109/CVPR52688.2022.01157 (CORE Ranked A*)},\n\tbooktitle = {{IEEE}/{CVF} {Conference} on {Computer} {Vision} and {Pattern} {Recognition}, {CVPR}-22, {New} {Orleans}, {Louisiana}, {US}, {Jun} 19-24, 2022},\n\tauthor = {Zhang, Miao and Pan, Shirui and Chang, Xiaojun and Su, Steven and Hu, Jilin and Haffari, Reza and Yang, Bin},\n\tyear = {2022},\n\tpages = {11861--11870},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Graph Self-Supervised Learning: A Survey.\n \n \n \n\n\n \n Liu, Y.; Jin, M.; Pan, S.; Zhou, C.; Zheng, Y.; Xia, F.; and Yu, P. S.\n\n\n \n\n\n\n
IEEE Transactions on Knowledge and Data Engineering (TKDE),1–21. 2022.\n
\n\n
\n\n
\n\n
\n\n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{liu_graph_2022,\n\ttitle = {Graph {Self}-{Supervised} {Learning}: {A} {Survey}},\n\tcopyright = {All rights reserved},\n\tdoi = {10.1109/TKDE.2022.3172903 (Impact Factor: 6.977; JCR Ranked Q1; Top Journal in Data Mining)},\n\tjournal = {IEEE Transactions on Knowledge and Data Engineering (TKDE)},\n\tauthor = {Liu, Yixin and Jin, Ming and Pan, Shirui and Zhou, Chuan and Zheng, Yu and Xia, Feng and Yu, Philip S.},\n\tyear = {2022},\n\tpages = {1--21},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Towards graph self-supervised learning with contrastive adjusted zooming.\n \n \n \n\n\n \n Liu, Y.; Jin, M.; Pan, S.; Zhou, C.; Zheng, Y.; Xia, F.; and Yu, P. S.\n\n\n \n\n\n\n
IEEE Transactions on Neural Networks and Learning Systems (TNNLS),1–15. 2022.\n
\n\n
\n\n
\n\n
\n\n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{liu_towards_2022,\n\ttitle = {Towards graph self-supervised learning with contrastive adjusted zooming},\n\tcopyright = {All rights reserved},\n\tdoi = {10.1109/TNNLS.2022.3216630},\n\tjournal = {IEEE Transactions on Neural Networks and Learning Systems (TNNLS)},\n\tauthor = {Liu, Yixin and Jin, Ming and Pan, Shirui and Zhou, Chuan and Zheng, Yu and Xia, Feng and Yu, Philip S.},\n\tyear = {2022},\n\tpages = {1--15},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Projective Ranking-based GNN Evasion Attacks.\n \n \n \n\n\n \n Zhang, H.; Yuan, X.; Zhou, C.; and Pan, S.\n\n\n \n\n\n\n
IEEE Transactions on Knowledge and Data Engineering (TKDE),1–14. 2022.\n
\n\n
\n\n
\n\n
\n\n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{zhang_projective_2022,\n\ttitle = {Projective {Ranking}-based {GNN} {Evasion} {Attacks}},\n\tcopyright = {All rights reserved},\n\tdoi = {10.1109/TKDE.2022.3219209 (Impact Factor: 6.977; JCR Ranked Q1; Top Journal in Data Mining)},\n\tjournal = {IEEE Transactions on Knowledge and Data Engineering (TKDE)},\n\tauthor = {Zhang, He and Yuan, Xingliang and Zhou, Chuan and Pan, Shirui},\n\tyear = {2022},\n\tpages = {1--14},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs.\n \n \n \n\n\n \n Jin, M.; Zheng, Y.; Li, Y.; Chen, S.; Yang, B.; and Pan, S.\n\n\n \n\n\n\n
IEEE Transactions on Knowledge and Data Engineering (TKDE),1–14. 2022.\n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{jin_multivariate_2022,\n\ttitle = {Multivariate {Time} {Series} {Forecasting} with {Dynamic} {Graph} {Neural} {ODEs}},\n\tcopyright = {All rights reserved},\n\tjournal = {IEEE Transactions on Knowledge and Data Engineering (TKDE)},\n\tauthor = {Jin, Ming and Zheng, Yu and Li, Yuan-Fang and Chen, Siheng and Yang, Bin and Pan, Shirui},\n\tyear = {2022},\n\tpages = {1--14},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Predicting Human Mobility via Graph Convolutional Dual-attentive Networks.\n \n \n \n\n\n \n Dang, W.; Wang, H.; Pan, S.; Zhang, P.; Zhou, C.; Chen, X.; and Wang, J.\n\n\n \n\n\n\n In
International Conference on Web Search and Data Mining (WSDM), pages 192–200, 2022. ACM\n
\n\n
\n\n
\n\n
\n\n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{dang_predicting_2022,\n\ttitle = {Predicting {Human} {Mobility} via {Graph} {Convolutional} {Dual}-attentive {Networks}},\n\tcopyright = {All rights reserved},\n\tdoi = {10.1145/3488560.3498400 (CORE Ranked A*)},\n\tbooktitle = {International {Conference} on {Web} {Search} and {Data} {Mining} ({WSDM})},\n\tpublisher = {ACM},\n\tauthor = {Dang, Weizhen and Wang, Haibo and Pan, Shirui and Zhang, Pei and Zhou, Chuan and Chen, Xin and Wang, Jilong},\n\tyear = {2022},\n\tpages = {192--200},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Towards Unsupervised Deep Graph Structure Learning.\n \n \n \n\n\n \n Liu, Y.; Zheng, Y.; Zhang, D.; Chen, H.; Peng, H.; and Pan, S.\n\n\n \n\n\n\n In
The Web Conference (WWW), Lyon, France 25 – 29 April 2022, pages 1392–1403, 2022. ACM\n
\n\n
\n\n
\n\n
\n\n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{liu_towards_2022,\n\ttitle = {Towards {Unsupervised} {Deep} {Graph} {Structure} {Learning}},\n\tcopyright = {All rights reserved},\n\tdoi = {10.1145/3485447.3512186 (CORE Ranked A*)},\n\tbooktitle = {The {Web} {Conference} ({WWW}), {Lyon}, {France} 25 – 29 {April} 2022},\n\tpublisher = {ACM},\n\tauthor = {Liu, Yixin and Zheng, Yu and Zhang, Daokun and Chen, Hongxu and Peng, Hao and Pan, Shirui},\n\tyear = {2022},\n\tpages = {1392--1403},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Towards Spatio-Temporal Aware Traffic Time Series Forecasting.\n \n \n \n\n\n \n Cirstea, R.; Yang, B.; Guo, C.; Kieu, T.; and Pan, S. P.\n\n\n \n\n\n\n In
IEEE International Conference on Data Engineering (ICDE-22), (Virtual) Kuala Lumpur, Malaysia, May 9-12, 2022 (CORE Ranked A*), 2022. \n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{cirstea_towards_2022,\n\ttitle = {Towards {Spatio}-{Temporal} {Aware} {Traffic} {Time} {Series} {Forecasting}},\n\tcopyright = {All rights reserved},\n\tbooktitle = {{IEEE} {International} {Conference} on {Data} {Engineering} ({ICDE}-22), ({Virtual}) {Kuala} {Lumpur}, {Malaysia}, {May} 9-12, 2022 ({CORE} {Ranked} {A}*)},\n\tauthor = {Cirstea, Razvan and Yang, Bin and Guo, Chenjuan and Kieu, Tung and Pan, Shirui Pan},\n\tyear = {2022},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Fire Burns, Swords Cut: Commonsense Inductive Bias for Exploration in Text-based Games.\n \n \n \n\n\n \n Ryu, D.; Shareghi, E.; Fang, M.; Xu, Y.; Pan, S.; and Haffari, R.\n\n\n \n\n\n\n In
60th Annual Meeting of the Association for Computational Linguistics (ACL-2022), Dublin, Ireland, May 22-27, 2022 (CORE Ranked A*), volume 2, pages 515–522, 2022. \n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{ryu_fire_2022,\n\ttitle = {Fire {Burns}, {Swords} {Cut}: {Commonsense} {Inductive} {Bias} for {Exploration} in {Text}-based {Games}},\n\tvolume = {2},\n\tcopyright = {All rights reserved},\n\tbooktitle = {60th {Annual} {Meeting} of the {Association} for {Computational} {Linguistics} ({ACL}-2022), {Dublin}, {Ireland}, {May} 22-27, 2022 ({CORE} {Ranked} {A}*)},\n\tauthor = {Ryu, Dongwon and Shareghi, Ehsan and Fang, Meng and Xu, Yunqiu and Pan, Shirui and Haffari, Reza},\n\tyear = {2022},\n\tpages = {515--522},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Exploring Relational Semantics for Inductive Knowledge Graph Completion.\n \n \n \n\n\n \n Wang, C.; Zhou, X.; Pan, S.; Dong, L.; Song, Z.; and Sha, Y.\n\n\n \n\n\n\n In
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Virtual Conference, Feburary 22- March 1, 2022 (CORE Ranked A*), 2022. AAAI Press\n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{wang_exploring_2022,\n\ttitle = {Exploring {Relational} {Semantics} for {Inductive} {Knowledge} {Graph} {Completion}},\n\tcopyright = {All rights reserved},\n\tbooktitle = {Proceedings of the {AAAI} {Conference} on {Artificial} {Intelligence} ({AAAI}), {Virtual} {Conference}, {Feburary} 22- {March} 1, 2022 ({CORE} {Ranked} {A}*)},\n\tpublisher = {AAAI Press},\n\tauthor = {Wang, Changjian and Zhou, Xiaofei and Pan, Shirui and Dong, Linhua and Song, Zeliang and Sha, Ying},\n\tyear = {2022},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Dual Space Graph Contrastive Learning.\n \n \n \n\n\n \n Yang, H.; Chen, H.; Pan, S.; Li, L.; Yu, P. S; and Xu, G.\n\n\n \n\n\n\n In
The Web Conference (WWW), Lyon, France 25 – 29 April 2022, pages 1238–1247, 2022. ACM\n
\n\n
\n\n
\n\n
\n\n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{yang_dual_2022,\n\ttitle = {Dual {Space} {Graph} {Contrastive} {Learning}},\n\tcopyright = {All rights reserved},\n\tdoi = {10.1145/3485447.3512211 (CORE Ranked A*)},\n\tbooktitle = {The {Web} {Conference} ({WWW}), {Lyon}, {France} 25 – 29 {April} 2022},\n\tpublisher = {ACM},\n\tauthor = {Yang, Haoran and Chen, Hongxu and Pan, Shirui and Li, Lin and Yu, Philip S and Xu, Guandong},\n\tyear = {2022},\n\tpages = {1238--1247},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n A Survey on Knowledge Graphs: Representation, Acquisition, and Applications.\n \n \n \n\n\n \n Ji, S.; Pan, S.; Cambria, E.; Marttinen, P.; and Yu, P. S\n\n\n \n\n\n\n
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 33(2): 494–514. 2022.\n
\n\n
\n\n
\n\n
\n\n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{ji_survey_2022,\n\ttitle = {A {Survey} on {Knowledge} {Graphs}: {Representation}, {Acquisition}, and {Applications}},\n\tvolume = {33},\n\tcopyright = {All rights reserved},\n\tdoi = {10.1109/TNNLS.2021.3070843 (Impact Factor: 10.451; JCR Ranked Q1)},\n\tnumber = {2},\n\tjournal = {IEEE Transactions on Neural Networks and Learning Systems (TNNLS)},\n\tauthor = {Ji, Shaoxiong and Pan, Shirui and Cambria, Erik and Marttinen, Pekka and Yu, Philip S},\n\tyear = {2022},\n\tpages = {494--514},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning.\n \n \n \n\n\n \n Liu, Y.; Li, Z.; Pan, S.; Gong, C.; Zhou, C.; and Karypis, G.\n\n\n \n\n\n\n
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 33(6): 2378–2392. 2022.\n
\n\n
\n\n
\n\n
\n\n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{liu_anomaly_2022,\n\ttitle = {Anomaly {Detection} on {Attributed} {Networks} via {Contrastive} {Self}-{Supervised} {Learning}},\n\tvolume = {33},\n\tcopyright = {All rights reserved},\n\tdoi = {10.1109/TNNLS.2021.3068344 (Impact Factor: 10.451; JCR Ranked Q1)},\n\tnumber = {6},\n\tjournal = {IEEE Transactions on Neural Networks and Learning Systems (TNNLS)},\n\tauthor = {Liu, Yixin and Li, Zhao and Pan, Shirui and Gong, Chen and Zhou, Chuan and Karypis, George},\n\tyear = {2022},\n\tpages = {2378--2392},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Dual Interactive Graph Convolutional Networks for Hyperspectral Image Classification.\n \n \n \n\n\n \n Wan, S.; Pan, S.; Zhong, P.; Chang, X.; Yang, J.; and Gong, C.\n\n\n \n\n\n\n
IEEE Transactions on Geoscience and Remote Sensing (TGRS), 60: 1–14. 2022.\n
\n\n
\n\n
\n\n
\n\n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{wan_dual_2022,\n\ttitle = {Dual {Interactive} {Graph} {Convolutional} {Networks} for {Hyperspectral} {Image} {Classification}},\n\tvolume = {60},\n\tcopyright = {All rights reserved},\n\tdoi = {10.1109/TGRS.2021.3075223 (Impact Factor: 5.6; JCR Ranked Q1)},\n\tjournal = {IEEE Transactions on Geoscience and Remote Sensing (TGRS)},\n\tauthor = {Wan, Sheng and Pan, Shirui and Zhong, Ping and Chang, Xiaojun and Yang, Jian and Gong, Chen},\n\tyear = {2022},\n\tpages = {1--14},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Attraction and Repulsion: Unsupervised Domain Adaptive Graph Contrastive Learning Network.\n \n \n \n\n\n \n Wu, M.; Pan, S.; and Zhu, X.\n\n\n \n\n\n\n
IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI),1. 2022.\n
\n\n
\n\n
\n\n
\n\n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{wu_attraction_2022,\n\ttitle = {Attraction and {Repulsion}: {Unsupervised} {Domain} {Adaptive} {Graph} {Contrastive} {Learning} {Network}},\n\tcopyright = {All rights reserved},\n\tdoi = {10.1109/TETCI.2022.3156044},\n\tjournal = {IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI)},\n\tauthor = {Wu, Man and Pan, Shirui and Zhu, Xingquan},\n\tyear = {2022},\n\tpages = {1},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n TraverseNet: Unifying Space and Time in Message Passing for Traffic Forecasting.\n \n \n \n\n\n \n Wu, Z.; Zheng, D.; Pan, S.; Gan, Q.; Long, G.; and Karypis, G.\n\n\n \n\n\n\n
IEEE Transactions on Neural Networks and Learning Systems (TNNLS),1–11. 2022.\n
\n\n
\n\n
\n\n
\n\n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{wu_traversenet:_2022,\n\ttitle = {{TraverseNet}: {Unifying} {Space} and {Time} in {Message} {Passing} for {Traffic} {Forecasting}},\n\tcopyright = {All rights reserved},\n\tdoi = {10.1109/TNNLS.2022.3186103},\n\tjournal = {IEEE Transactions on Neural Networks and Learning Systems (TNNLS)},\n\tauthor = {Wu, Zonghan and Zheng, Da and Pan, Shirui and Gan, Quan and Long, Guodong and Karypis, George},\n\tyear = {2022},\n\tpages = {1--11},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Discrete embedding for attributed graphs.\n \n \n \n\n\n \n Yang, H.; Chen, L.; Pan, S.; Wang, H.; and Zhang, P.\n\n\n \n\n\n\n
Pattern Recognition (PR), 123: 108368. 2022.\n
Publisher: Elsevier\n\n
\n\n
\n\n
\n\n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{yang_discrete_2022,\n\ttitle = {Discrete embedding for attributed graphs},\n\tvolume = {123},\n\tcopyright = {All rights reserved},\n\tdoi = {10.1016/j.patcog.2021.108368 (Impact Factor: 7.74; JCR Ranked Q1)},\n\tjournal = {Pattern Recognition (PR)},\n\tauthor = {Yang, Hong and Chen, Ling and Pan, Shirui and Wang, Haishuai and Zhang, Peng},\n\tyear = {2022},\n\tnote = {Publisher: Elsevier},\n\tpages = {108368},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Task Scheduling in Three-Dimensional Spatial Crowdsourcing: A Social Welfare Perspective.\n \n \n \n\n\n \n Wang, L.; Yang, D.; Yu, Z.; Xiong, F.; Han, L.; Pan, S.; and Guo, B.\n\n\n \n\n\n\n
IEEE Transactions on Mobile Computing (TMC),1–1. 2022.\n
\n\n
\n\n
\n\n
\n\n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{wang_task_2022,\n\ttitle = {Task {Scheduling} in {Three}-{Dimensional} {Spatial} {Crowdsourcing}: {A} {Social} {Welfare} {Perspective}},\n\tcopyright = {All rights reserved},\n\tdoi = {10.1109/TMC.2022.3175305},\n\tjournal = {IEEE Transactions on Mobile Computing (TMC)},\n\tauthor = {Wang, Liang and Yang, Dingqi and Yu, Zhiwen and Xiong, Fei and Han, Lei and Pan, Shirui and Guo, Bin},\n\tyear = {2022},\n\tpages = {1--1},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Compact Scheduling for Task Graph Oriented Mobile Crowdsourcing.\n \n \n \n\n\n \n Wang, L.; Yu, Z.; Han, Q.; Yang, D.; Pan, S.; Yao, Y.; and Zhang, D.\n\n\n \n\n\n\n
IEEE Transactions on Mobile Computing (TMC), 21(7): 2358–2371. 2022.\n
\n\n
\n\n
\n\n
\n\n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{wang_compact_2022,\n\ttitle = {Compact {Scheduling} for {Task} {Graph} {Oriented} {Mobile} {Crowdsourcing}},\n\tvolume = {21},\n\tcopyright = {All rights reserved},\n\tdoi = {10.1109/TMC.2020.3040007},\n\tnumber = {7},\n\tjournal = {IEEE Transactions on Mobile Computing (TMC)},\n\tauthor = {Wang, Liang and Yu, Zhiwen and Han, Qi and Yang, Dingqi and Pan, Shirui and Yao, Yuan and Zhang, Daqing},\n\tyear = {2022},\n\tpages = {2358--2371},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Beyond low-pass filtering: Graph convolutional networks with automatic filtering.\n \n \n \n\n\n \n Wu, Z.; Pan, S.; Long, G.; Jiang, J.; and Zhang, C.\n\n\n \n\n\n\n
IEEE Transactions on Knowledge and Data Engineering (TKDE),1–12. 2022.\n
\n\n
\n\n
\n\n
\n\n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{wu_beyond_2022,\n\ttitle = {Beyond low-pass filtering: {Graph} convolutional networks with automatic filtering},\n\tcopyright = {All rights reserved},\n\tdoi = {10.1109/TKDE.2022.3186016},\n\tjournal = {IEEE Transactions on Knowledge and Data Engineering (TKDE)},\n\tauthor = {Wu, Zonghan and Pan, Shirui and Long, Guodong and Jiang, Jing and Zhang, Chengqi},\n\tyear = {2022},\n\tpages = {1--12},\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n One-shot Learning-based Animal Video Segmentation.\n \n \n \n\n\n \n Xue, T.; Qiao, Y.; Kong, H.; Su, D.; Pan, S.; Rafique, K.; and Sukkarieh, S.\n\n\n \n\n\n\n
IEEE Transactions on Industrial Informatics (TII), 18(6): 3799–3807. 2022.\n
\n\n
\n\n
\n\n
\n\n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{xue_one-shot_2022,\n\ttitle = {One-shot {Learning}-based {Animal} {Video} {Segmentation}},\n\tvolume = {18},\n\tcopyright = {All rights reserved},\n\tdoi = {10.1109/TII.2021.3117020 (Impact Factor: 10.215; JCR Ranked Q1)},\n\tnumber = {6},\n\tjournal = {IEEE Transactions on Industrial Informatics (TII)},\n\tauthor = {Xue, Tengfei and Qiao, Yongliang and Kong, He and Su, Daobilige and Pan, Shirui and Rafique, Khalid and Sukkarieh, Salah},\n\tyear = {2022},\n\tpages = {3799--3807},\n}\n
\n
\n\n\n\n
\n\n\n\n\n\n