Graph neural networks: A review of methods and applications. Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., & Sun, M. AI Open, 1(September 2020):57-81, Elsevier Ltd, 2020.
![Graph neural networks: A review of methods and applications [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper ![Graph neural networks: A review of methods and applications [link]](https://bibbase.org/img/filetypes/link.svg "link")
Website doi abstract bibtex
Paper Website doi abstract bibtex Lots of learning tasks require dealing with graph data which contains rich relation information among elements. Modeling physics systems, learning molecular fingerprints, predicting protein interface, and classifying diseases demand a model to learn from graph inputs. In other domains such as learning from non-structural data like texts and images, reasoning on extracted structures (like the dependency trees of sentences and the scene graphs of images) is an important research topic which also needs graph reasoning models. Graph neural networks (GNNs) are neural models that capture the dependence of graphs via message passing between the nodes of graphs. In recent years, variants of GNNs such as graph convolutional network (GCN), graph attention network (GAT), graph recurrent network (GRN) have demonstrated ground-breaking performances on many deep learning tasks. In this survey, we propose a general design pipeline for GNN models and discuss the variants of each component, systematically categorize the applications, and propose four open problems for future research.
@article{
title = {Graph neural networks: A review of methods and applications},
type = {article},
year = {2020},
pages = {57-81},
volume = {1},
websites = {https://doi.org/10.1016/j.aiopen.2021.01.001},
publisher = {Elsevier Ltd},
id = {39388a6c-0465-3da0-92e1-c6fa1b38208f},
created = {2021-08-17T08:06:02.964Z},
file_attached = {true},
profile_id = {f3d36c73-062b-3738-9a74-d09e4e83eb1e},
group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},
last_modified = {2021-10-01T15:59:25.056Z},
read = {true},
starred = {true},
authored = {false},
confirmed = {true},
hidden = {false},
citation_key = {Zhou2020},
folder_uuids = {dbd9a6d6-88f6-4a62-9acd-402fb473145a},
private_publication = {false},
abstract = {Lots of learning tasks require dealing with graph data which contains rich relation information among elements. Modeling physics systems, learning molecular fingerprints, predicting protein interface, and classifying diseases demand a model to learn from graph inputs. In other domains such as learning from non-structural data like texts and images, reasoning on extracted structures (like the dependency trees of sentences and the scene graphs of images) is an important research topic which also needs graph reasoning models. Graph neural networks (GNNs) are neural models that capture the dependence of graphs via message passing between the nodes of graphs. In recent years, variants of GNNs such as graph convolutional network (GCN), graph attention network (GAT), graph recurrent network (GRN) have demonstrated ground-breaking performances on many deep learning tasks. In this survey, we propose a general design pipeline for GNN models and discuss the variants of each component, systematically categorize the applications, and propose four open problems for future research.},
bibtype = {article},
author = {Zhou, Jie and Cui, Ganqu and Hu, Shengding and Zhang, Zhengyan and Yang, Cheng and Liu, Zhiyuan and Wang, Lifeng and Li, Changcheng and Sun, Maosong},
doi = {10.1016/j.aiopen.2021.01.001},
journal = {AI Open},
number = {September 2020}
}Downloads: 0
{"_id":"kcWaGgyuNydgTEhYW","bibbaseid":"zhou-cui-hu-zhang-yang-liu-wang-li-etal-graphneuralnetworksareviewofmethodsandapplications-2020","author_short":["Zhou, J.","Cui, G.","Hu, S.","Zhang, Z.","Yang, C.","Liu, Z.","Wang, L.","Li, C.","Sun, M."],"bibdata":{"title":"Graph neural networks: A review of methods and applications","type":"article","year":"2020","pages":"57-81","volume":"1","websites":"https://doi.org/10.1016/j.aiopen.2021.01.001","publisher":"Elsevier Ltd","id":"39388a6c-0465-3da0-92e1-c6fa1b38208f","created":"2021-08-17T08:06:02.964Z","file_attached":"true","profile_id":"f3d36c73-062b-3738-9a74-d09e4e83eb1e","group_id":"1ff583c0-be37-34fa-9c04-73c69437d354","last_modified":"2021-10-01T15:59:25.056Z","read":"true","starred":"true","authored":false,"confirmed":"true","hidden":false,"citation_key":"Zhou2020","folder_uuids":"dbd9a6d6-88f6-4a62-9acd-402fb473145a","private_publication":false,"abstract":"Lots of learning tasks require dealing with graph data which contains rich relation information among elements. Modeling physics systems, learning molecular fingerprints, predicting protein interface, and classifying diseases demand a model to learn from graph inputs. In other domains such as learning from non-structural data like texts and images, reasoning on extracted structures (like the dependency trees of sentences and the scene graphs of images) is an important research topic which also needs graph reasoning models. Graph neural networks (GNNs) are neural models that capture the dependence of graphs via message passing between the nodes of graphs. In recent years, variants of GNNs such as graph convolutional network (GCN), graph attention network (GAT), graph recurrent network (GRN) have demonstrated ground-breaking performances on many deep learning tasks. In this survey, we propose a general design pipeline for GNN models and discuss the variants of each component, systematically categorize the applications, and propose four open problems for future research.","bibtype":"article","author":"Zhou, Jie and Cui, Ganqu and Hu, Shengding and Zhang, Zhengyan and Yang, Cheng and Liu, Zhiyuan and Wang, Lifeng and Li, Changcheng and Sun, Maosong","doi":"10.1016/j.aiopen.2021.01.001","journal":"AI Open","number":"September 2020","bibtex":"@article{\n title = {Graph neural networks: A review of methods and applications},\n type = {article},\n year = {2020},\n pages = {57-81},\n volume = {1},\n websites = {https://doi.org/10.1016/j.aiopen.2021.01.001},\n publisher = {Elsevier Ltd},\n id = {39388a6c-0465-3da0-92e1-c6fa1b38208f},\n created = {2021-08-17T08:06:02.964Z},\n file_attached = {true},\n profile_id = {f3d36c73-062b-3738-9a74-d09e4e83eb1e},\n group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},\n last_modified = {2021-10-01T15:59:25.056Z},\n read = {true},\n starred = {true},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {Zhou2020},\n folder_uuids = {dbd9a6d6-88f6-4a62-9acd-402fb473145a},\n private_publication = {false},\n abstract = {Lots of learning tasks require dealing with graph data which contains rich relation information among elements. Modeling physics systems, learning molecular fingerprints, predicting protein interface, and classifying diseases demand a model to learn from graph inputs. In other domains such as learning from non-structural data like texts and images, reasoning on extracted structures (like the dependency trees of sentences and the scene graphs of images) is an important research topic which also needs graph reasoning models. Graph neural networks (GNNs) are neural models that capture the dependence of graphs via message passing between the nodes of graphs. In recent years, variants of GNNs such as graph convolutional network (GCN), graph attention network (GAT), graph recurrent network (GRN) have demonstrated ground-breaking performances on many deep learning tasks. In this survey, we propose a general design pipeline for GNN models and discuss the variants of each component, systematically categorize the applications, and propose four open problems for future research.},\n bibtype = {article},\n author = {Zhou, Jie and Cui, Ganqu and Hu, Shengding and Zhang, Zhengyan and Yang, Cheng and Liu, Zhiyuan and Wang, Lifeng and Li, Changcheng and Sun, Maosong},\n doi = {10.1016/j.aiopen.2021.01.001},\n journal = {AI Open},\n number = {September 2020}\n}","author_short":["Zhou, J.","Cui, G.","Hu, S.","Zhang, Z.","Yang, C.","Liu, Z.","Wang, L.","Li, C.","Sun, M."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c/file/5ea81a61-8ab8-d7b5-10c0-12d132445ac2/Graph_neural_networks_A_review_of_methods_and_applications.pdf.pdf","Website":"https://doi.org/10.1016/j.aiopen.2021.01.001"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"zhou-cui-hu-zhang-yang-liu-wang-li-etal-graphneuralnetworksareviewofmethodsandapplications-2020","role":"author","metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","dataSources":["KhfhF8P52iu5Szymq","ya2CyA73rpZseyrZ8","CmHEoydhafhbkXXt5","2252seNhipfTmjEBQ"],"keywords":[],"search_terms":["graph","neural","networks","review","methods","applications","zhou","cui","hu","zhang","yang","liu","wang","li","sun"],"title":"Graph neural networks: A review of methods and applications","year":2020}