A Comprehensive Survey on Graph Neural Networks. Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. arXiv:1901.00596 [cs, stat], 12, 2019. arXiv: 1901.00596![A Comprehensive Survey on Graph Neural Networks [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this survey, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. We propose a new taxonomy to divide the state-of-the-art graph neural networks into four categories, namely recurrent graph neural networks, convolutional graph neural networks, graph autoencoders and spatial-temporal graph neural networks. We further discuss the applications of graph neural networks across various domains and summarize the open source codes and benchmarks of the existing algorithms on different learning tasks. Finally, we propose potential research directions in this rapidly growing field.
@article{wu_comprehensive_2019,
abstract = {Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this survey, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. We propose a new taxonomy to divide the state-of-the-art graph neural networks into four categories, namely recurrent graph neural networks, convolutional graph neural networks, graph autoencoders and spatial-temporal graph neural networks. We further discuss the applications of graph neural networks across various domains and summarize the open source codes and benchmarks of the existing algorithms on different learning tasks. Finally, we propose potential research directions in this rapidly growing field.},
added-at = {2020-02-21T16:09:44.000+0100},
author = {Wu, Zonghan and Pan, Shirui and Chen, Fengwen and Long, Guodong and Zhang, Chengqi and Yu, Philip S.},
biburl = {https://www.bibsonomy.org/bibtex/26e2f75da0827c0288df78183ce6255c0/tschumacher},
file = {Wu et al - A Comprehensive Survey on Graph Neural Networks.pdf:C\:\\Users\\Admin\\Documents\\Research\\_Paperbase\\Graph Embeddings\\Wu et al - A Comprehensive Survey on Graph Neural Networks.pdf:application/pdf},
interhash = {e6df299a7965fc0158ecd71e6d922246},
intrahash = {6e2f75da0827c0288df78183ce6255c0},
journal = {arXiv:1901.00596 [cs, stat]},
keywords = {Survey GNN Embedding_Algorithm Node_Embeddings},
language = {en},
month = {12},
note = {arXiv: 1901.00596},
timestamp = {2020-02-21T16:09:44.000+0100},
title = {A {Comprehensive} {Survey} on {Graph} {Neural} {Networks}},
url = {http://arxiv.org/abs/1901.00596},
urldate = {2019-12-10},
year = 2019
}
Downloads: 0
{"_id":"mDyk7z3uYBSSDeEqt","bibbaseid":"wu-pan-chen-long-zhang-yu-acomprehensivesurveyongraphneuralnetworks-2019","authorIDs":["561c75c18d7cb332200004ce","FgTRy7pNrBNcDn5rk","k6fB9cczWrDbvaPzR"],"author_short":["Wu, Z.","Pan, S.","Chen, F.","Long, G.","Zhang, C.","Yu, P. S."],"bibdata":{"bibtype":"article","type":"article","abstract":"Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this survey, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. We propose a new taxonomy to divide the state-of-the-art graph neural networks into four categories, namely recurrent graph neural networks, convolutional graph neural networks, graph autoencoders and spatial-temporal graph neural networks. We further discuss the applications of graph neural networks across various domains and summarize the open source codes and benchmarks of the existing algorithms on different learning tasks. Finally, we propose potential research directions in this rapidly growing field.","added-at":"2020-02-21T16:09:44.000+0100","author":[{"propositions":[],"lastnames":["Wu"],"firstnames":["Zonghan"],"suffixes":[]},{"propositions":[],"lastnames":["Pan"],"firstnames":["Shirui"],"suffixes":[]},{"propositions":[],"lastnames":["Chen"],"firstnames":["Fengwen"],"suffixes":[]},{"propositions":[],"lastnames":["Long"],"firstnames":["Guodong"],"suffixes":[]},{"propositions":[],"lastnames":["Zhang"],"firstnames":["Chengqi"],"suffixes":[]},{"propositions":[],"lastnames":["Yu"],"firstnames":["Philip","S."],"suffixes":[]}],"biburl":"https://www.bibsonomy.org/bibtex/26e2f75da0827c0288df78183ce6255c0/tschumacher","file":"Wu et al - A Comprehensive Survey on Graph Neural Networks.pdf:C\\:\\\\Users\\\\Admin\\\\Documents\\\\Research\\_Paperbase\\\\Graph Embeddings\\\\Wu et al - A Comprehensive Survey on Graph Neural Networks.pdf:application/pdf","interhash":"e6df299a7965fc0158ecd71e6d922246","intrahash":"6e2f75da0827c0288df78183ce6255c0","journal":"arXiv:1901.00596 [cs, stat]","keywords":"Survey GNN Embedding_Algorithm Node_Embeddings","language":"en","month":"12","note":"arXiv: 1901.00596","timestamp":"2020-02-21T16:09:44.000+0100","title":"A Comprehensive Survey on Graph Neural Networks","url":"http://arxiv.org/abs/1901.00596","urldate":"2019-12-10","year":"2019","bibtex":"@article{wu_comprehensive_2019,\n abstract = {Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this survey, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. We propose a new taxonomy to divide the state-of-the-art graph neural networks into four categories, namely recurrent graph neural networks, convolutional graph neural networks, graph autoencoders and spatial-temporal graph neural networks. We further discuss the applications of graph neural networks across various domains and summarize the open source codes and benchmarks of the existing algorithms on different learning tasks. Finally, we propose potential research directions in this rapidly growing field.},\n added-at = {2020-02-21T16:09:44.000+0100},\n author = {Wu, Zonghan and Pan, Shirui and Chen, Fengwen and Long, Guodong and Zhang, Chengqi and Yu, Philip S.},\n biburl = {https://www.bibsonomy.org/bibtex/26e2f75da0827c0288df78183ce6255c0/tschumacher},\n file = {Wu et al - A Comprehensive Survey on Graph Neural Networks.pdf:C\\:\\\\Users\\\\Admin\\\\Documents\\\\Research\\\\_Paperbase\\\\Graph Embeddings\\\\Wu et al - A Comprehensive Survey on Graph Neural Networks.pdf:application/pdf},\n interhash = {e6df299a7965fc0158ecd71e6d922246},\n intrahash = {6e2f75da0827c0288df78183ce6255c0},\n journal = {arXiv:1901.00596 [cs, stat]},\n keywords = {Survey GNN Embedding_Algorithm Node_Embeddings},\n language = {en},\n month = {12},\n note = {arXiv: 1901.00596},\n timestamp = {2020-02-21T16:09:44.000+0100},\n title = {A {Comprehensive} {Survey} on {Graph} {Neural} {Networks}},\n url = {http://arxiv.org/abs/1901.00596},\n urldate = {2019-12-10},\n year = 2019\n}\n\n","author_short":["Wu, Z.","Pan, S.","Chen, F.","Long, G.","Zhang, C.","Yu, P. S."],"key":"wu_comprehensive_2019-1","id":"wu_comprehensive_2019-1","bibbaseid":"wu-pan-chen-long-zhang-yu-acomprehensivesurveyongraphneuralnetworks-2019","role":"author","urls":{"Paper":"http://arxiv.org/abs/1901.00596"},"keyword":["Survey GNN Embedding_Algorithm Node_Embeddings"],"metadata":{"authorlinks":{"pan, s":"https://shiruipan.github.io/post/selectedpub/","pan, s":"https://bibbase.org/service/mendeley/079852a8-52df-3ac8-a41c-8bebd97d6b2b"}},"downloads":0},"bibtype":"article","biburl":"http://www.bibsonomy.org/bib/author/pan, shirui?items=1000","creationDate":"2019-11-29T05:29:58.842Z","downloads":0,"keywords":["survey gnn embedding_algorithm node_embeddings"],"search_terms":["comprehensive","survey","graph","neural","networks","wu","pan","chen","long","zhang","yu"],"title":"A Comprehensive Survey on Graph Neural Networks","year":2019,"dataSources":["mKA5vx6kcS6ikoYhW","ya2CyA73rpZseyrZ8","AoeZNpAr9D2ciGMwa","6yXn8CtuzyEbCSr2m"]}