A Comprehensive Survey on Graph Neural Networks

被引:6625
作者
Wu, Zonghan [1 ]
Pan, Shirui [2 ]
Chen, Fengwen [1 ]
Long, Guodong [1 ]
Zhang, Chengqi [1 ]
Yu, Philip S. [3 ]
机构
[1] Univ Technol Sydney, Fac Engn & Informat Technol, Ctr Artificial Intelligence, Ultimo, NSW 2007, Australia
[2] Monash Univ, Fac Informat Technol, Clayton, Vic 3800, Australia
[3] Univ Illinois, Dept Comp Sci, Chicago, IL 60607 USA
基金
澳大利亚研究理事会;
关键词
Deep learning; Neural networks; Task analysis; Kernel; Feature extraction; Data mining; Learning systems; graph autoencoder (GAE); graph convolutional networks (GCNs); graph neural networks (GNNs); graph representation learning; network embedding; CONVOLUTIONAL NETWORKS; CLASSIFICATION;
D O I
10.1109/TNNLS.2020.2978386
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页码:4 / 24
页数:21
相关论文
共 172 条
[1]  
Abu-El-Haija S, 2018, ADV NEUR IN, V31
[2]  
Allamanis M., 2018, Learning to represent programs with graphs
[3]  
[Anonymous], 2017, IEEE J-STSP, DOI [10.1109/JSTSP.2017.2726981, DOI 10.1109/JSTSP.2017.2726981]
[4]  
[Anonymous], 2017, PMLR
[5]  
Arjovsky M., 2017, arXiv preprint arXiv:1701.07875
[6]  
Atwood J, 2016, ADV NEUR IN, V29
[7]  
Bacciu D., 2018, P ICML, P1
[8]  
Bastings J., 2017, P 2017 C EMPIRICAL M, P1957
[9]  
Battaglia Peter W, 2018, Relational inductive biases, deep learning, and graph networks
[10]  
Beck D, 2018, PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL), VOL 1, P273