A Comprehensive Survey on Graph Neural Networks. Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P., S. IEEE Transactions on Neural Networks and Learning Systems, 32(1):4-24, IEEE, 2021.
![A Comprehensive Survey on Graph Neural Networks [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper doi abstract bibtex
Paper doi 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 the existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this article, 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 GNNs into four categories, namely, recurrent GNNs, convolutional GNNs, graph autoencoders, and spatial-Temporal GNNs. We further discuss the applications of GNNs across various domains and summarize the open-source codes, benchmark data sets, and model evaluation of GNNs. Finally, we propose potential research directions in this rapidly growing field.
@article{
title = {A Comprehensive Survey on Graph Neural Networks},
type = {article},
year = {2021},
keywords = {Deep learning,graph autoencoder (GAE),graph convolutional networks (GCNs),graph neural networks (GNNs),graph representation learning,network embedding},
pages = {4-24},
volume = {32},
publisher = {IEEE},
id = {9bdff10a-f897-3446-8652-8a28b7f6b8c5},
created = {2021-08-17T08:06:02.968Z},
file_attached = {true},
profile_id = {f3d36c73-062b-3738-9a74-d09e4e83eb1e},
group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},
last_modified = {2021-09-30T15:38:16.106Z},
read = {true},
starred = {true},
authored = {false},
confirmed = {true},
hidden = {false},
citation_key = {Wu2021},
folder_uuids = {dbd9a6d6-88f6-4a62-9acd-402fb473145a},
private_publication = {false},
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 the existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this article, 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 GNNs into four categories, namely, recurrent GNNs, convolutional GNNs, graph autoencoders, and spatial-Temporal GNNs. We further discuss the applications of GNNs across various domains and summarize the open-source codes, benchmark data sets, and model evaluation of GNNs. Finally, we propose potential research directions in this rapidly growing field.},
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},
number = {1}
}Downloads: 0
{"_id":"H9x4iH9s4i4nTCtRC","bibbaseid":"wu-pan-chen-long-zhang-yu-acomprehensivesurveyongraphneuralnetworks-2021","authorIDs":["FgTRy7pNrBNcDn5rk"],"author_short":["Wu, Z.","Pan, S.","Chen, F.","Long, G.","Zhang, C.","Yu, P., S."],"bibdata":{"title":"A Comprehensive Survey on Graph Neural Networks","type":"article","year":"2021","keywords":"Deep learning,graph autoencoder (GAE),graph convolutional networks (GCNs),graph neural networks (GNNs),graph representation learning,network embedding","pages":"4-24","volume":"32","publisher":"IEEE","id":"9bdff10a-f897-3446-8652-8a28b7f6b8c5","created":"2021-08-17T08:06:02.968Z","file_attached":"true","profile_id":"f3d36c73-062b-3738-9a74-d09e4e83eb1e","group_id":"1ff583c0-be37-34fa-9c04-73c69437d354","last_modified":"2021-09-30T15:38:16.106Z","read":"true","starred":"true","authored":false,"confirmed":"true","hidden":false,"citation_key":"Wu2021","folder_uuids":"dbd9a6d6-88f6-4a62-9acd-402fb473145a","private_publication":false,"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 the existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this article, 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 GNNs into four categories, namely, recurrent GNNs, convolutional GNNs, graph autoencoders, and spatial-Temporal GNNs. We further discuss the applications of GNNs across various domains and summarize the open-source codes, benchmark data sets, and model evaluation of GNNs. Finally, we propose potential research directions in this rapidly growing field.","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","number":"1","bibtex":"@article{\n title = {A Comprehensive Survey on Graph Neural Networks},\n type = {article},\n year = {2021},\n keywords = {Deep learning,graph autoencoder (GAE),graph convolutional networks (GCNs),graph neural networks (GNNs),graph representation learning,network embedding},\n pages = {4-24},\n volume = {32},\n publisher = {IEEE},\n id = {9bdff10a-f897-3446-8652-8a28b7f6b8c5},\n created = {2021-08-17T08:06:02.968Z},\n file_attached = {true},\n profile_id = {f3d36c73-062b-3738-9a74-d09e4e83eb1e},\n group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},\n last_modified = {2021-09-30T15:38:16.106Z},\n read = {true},\n starred = {true},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {Wu2021},\n folder_uuids = {dbd9a6d6-88f6-4a62-9acd-402fb473145a},\n private_publication = {false},\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 the existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this article, 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 GNNs into four categories, namely, recurrent GNNs, convolutional GNNs, graph autoencoders, and spatial-Temporal GNNs. We further discuss the applications of GNNs across various domains and summarize the open-source codes, benchmark data sets, and model evaluation of GNNs. Finally, we propose potential research directions in this rapidly growing field.},\n bibtype = {article},\n author = {Wu, Zonghan and Pan, Shirui and Chen, Fengwen and Long, Guodong and Zhang, Chengqi and Yu, Philip S.},\n doi = {10.1109/TNNLS.2020.2978386},\n journal = {IEEE Transactions on Neural Networks and Learning Systems},\n number = {1}\n}","author_short":["Wu, Z.","Pan, S.","Chen, F.","Long, G.","Zhang, C.","Yu, P., S."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c/file/5bfcd1f4-9cf8-d4e5-7c87-70fe95545bee/A_Comprehensive_Survey_on_Graph_Neural_Networks.pdf.pdf"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"wu-pan-chen-long-zhang-yu-acomprehensivesurveyongraphneuralnetworks-2021","role":"author","keyword":["Deep learning","graph autoencoder (GAE)","graph convolutional networks (GCNs)","graph neural networks (GNNs)","graph representation learning","network embedding"],"metadata":{"authorlinks":{"pan, s":"https://shiruipan.github.io/post/selectedpub/"}},"downloads":0},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","creationDate":"2021-02-15T10:01:15.148Z","downloads":0,"keywords":["deep learning","graph autoencoder (gae)","graph convolutional networks (gcns)","graph neural networks (gnns)","graph representation learning","network embedding"],"search_terms":["comprehensive","survey","graph","neural","networks","wu","pan","chen","long","zhang","yu"],"title":"A Comprehensive Survey on Graph Neural Networks","year":2021,"dataSources":["mKA5vx6kcS6ikoYhW","ya2CyA73rpZseyrZ8","AoeZNpAr9D2ciGMwa","fcdT59YHNhp9Euu5k","m7B7iLMuqoXuENyof","CmHEoydhafhbkXXt5","6yXn8CtuzyEbCSr2m"]}