图神经网络综述

doi:10.19678/j.issn.1000-3428.0058382

摘要/Abstract

摘要： 随着互联网和计算机信息技术的不断发展，图神经网络已成为人工智能和大数据处理领域的重要研究方向。图神经网络可对相邻节点间的信息进行有效传播和聚合，并将深度学习理念应用于非欧几里德空间的数据处理中。简述图计算、图数据库、知识图谱、图神经网络等图结构的相关研究进展，从频域和空间域角度分析与比较基于不同信息聚合方式的图神经网络结构，重点讨论图神经网络与深度学习技术相结合的研究领域，总结归纳图神经网络在动作检测、图系统、文本和图像处理任务中的具体应用，并对图神经网络未来的发展方向进行展望。

关键词: 图神经网络, 图结构, 图计算, 深度学习, 频域, 空间域

Abstract: With the continuous development of the computer and Internet technologies,graph neural network has become an important research area in artificial intelligence and big data.Graph neural network can effectively transmit and aggregate information between neighboring nodes,and applies the concept of deep learning to the data processing of non-Euclidean space.This paper briefly introduces the research progress of graph computing,graph database,knowledge graph,graph neural network and other graph-based techniques.It also analyses and compares graph neural network structures based on different information aggregation modes in the spectral and spatial domain.Then the paper discusses research fields that combine graph neural network with deep learning,and summarizes the specific applications of graph neural networks in action detection,graph systems,text and image processing tasks.Finally,it prospects the future development research directions of graph neural networks.

Key words: graph neural network, graph structure, graph computing, deep learning, spectral domain, spatial domain

中图分类号:

TP18

王健宗, 孔令炜, 黄章成, 肖京. 图神经网络综述[J]. 计算机工程, 2021, 47(4): 1-12.

WANG Jianzong, KONG Lingwei, HUANG Zhangcheng, XIAO Jing. Survey of Graph Neural Network[J]. Computer Engineering, 2021, 47(4): 1-12.

http://www.ecice06.com/CN/Y2021/V47/I4/1

图/表 8

20210425164138

20210425164142

20210425164148

20210425164151

20210425164155

20210425164158

20210425164201

20210425164204

参考文献

[1] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems.New York,USA:ACM Press,2012:1097-1105.
[2] TRUDEAU R J.Introduction to graph theory[M].Upper Saddle River,USA:Prentice Hall,1996.
[3] WANG Xin,XU Qiang,CHAI Lele,et al.Efficient distributed query processing on large scale RDF graph data[J].Journal of Software,2019,30(3):498-514.(in Chinese)王鑫,徐强,柴乐乐,等.大规模RDF图数据上高效率分布式查询处理[J].软件学报,2019,30(3):498-514.
[4] WANG Chengbin,MA Xiaogang,CHEN Jianguo,et al.Information extraction and knowledge graph construction from geoscience literature[J].Computers & Geosciences,2018,112:112-120.
[5] WANG Xin,ZOU Lei,WANG Chaokun,et al.Research on knowledge graph data management:a survey[J].Journal of Software,2019,30(7):2139-2174.(in Chinese)王鑫,邹磊,王朝坤,等.知识图谱数据管理研究综述[J].软件学报,2019,30(7):2139-2174.
[6] WANG Xin,CHEN Weixue,YANG Yajun,et al.Research on knowledge graph partitioning algorithms:a survey[J].Chinese Journal of Computers,2021,44(1):236-259.(in Chinese)王鑫,陈蔚雪,杨雅君,等.知识图谱划分算法研究综述[J].计算机学报,2021,44(1):236-259.
[7] WANG Xin,FU Qiang,WANG Lin,et al.Survey on visualization query technology of knowledge graph[J].Computer Engineering,2020,46(6):1-11.(in Chinese)王鑫,傅强,王林,等.知识图谱可视化查询技术综述[J].计算机工程,2020,46(6):1-11.
[8] LI Zhongfei,YANG Yajun,WANG Xin.Rule based shortest path query algorithm[J].Journal of Software,2019,30(3):515-536.(in Chinese)李忠飞,杨雅君,王鑫.基于规则的最短路径查询算法研究[J].软件学报,2019,30(3):515-536.
[9] MOHAMMAD A H,VACHIK S D.Triangle counting in large networks:a review[EB/OL].[2020-04-12].https://onlinelibrary.wiley.com/doi/abs/10.1002/widm.1226.
[10] BRUNA J,ZAREMBA W,SZLAM A,et al.Spectral net-works and locally connected networks on graphs[EB/OL].[2020-04-12].https://arxiv.org/abs/1312.6203.
[11] DEFFERRARD M,BRESSON X,VANDERGHEYNST P.Convolutional neural networks on graphs with fast localized spectral filtering[EB/OL].[2020-04-12].https://arxiv.org/abs/1606.09375.
[12] BATTAGLIA P W.Relational inductive biases,deep learning,and graph networks[EB/OL].[2020-04-12].https://arxiv.org/abs/1806.01261v3.
[13] ZHANG Ziwei,CUI Peng,ZHU Wenwu.Deep learning on graphs:a survey[EB/OL].[2020-04-12].https://ieeexplore.ieee.org/document/9039675.
[14] ZHOU Jie,CUI Ganqu,ZHANG Zhengyan,et al.Graph neural networks:a review of methods and applications[EB/OL].[2020-04-12].https://arxiv.org/abs/1812.08434.
[15] WU Zonghan,PAN Shirui,CHEN Fengwen,et al.A comprehensive survey on graph neural networks[J].IEEE Transactions on Neural Networks and Learning Systems,2021,32(1):4-21.
[16] MATHIAS N,AHMED M,KUTZKOV K.Learning convolutional neural networks for graphs[C]//Proceedings of the 33rd International Conference on Machine Learning.New York,USA:ACM Press 2016:2014-2023.
[17] KAMPFFMEYER M,CHEN Y,LIANG X,et al.Rethink-ing knowledge graph propagation for zero-shot learning[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2019:11479-11488.
[18] DUAN Dongsheng,LI Yuhua,JIN Yanan,et al.Community mining on dynamic weighted directed graphs[C]//Proceedings of the 1st ACM International Workshop on Complex Networks Meet Information & Knowledge Management.New York,USA:ACM Press,2009:11-18.
[19] BECK D,HAFFARI G,COHN T.Graph-to-sequence learning using gated graph neural networks[EB/OL].[2020-04-12].http://arxiv.org/abs/1806.09835.
[20] ZHANG Yizhou,XIONG Yun,KONG Xiangnan,et al.Deep collective classification in heterogeneous information networks[C]//Proceedings of 2018 World Wide Web Conference.New York,USA:ACM Press,2018:399-408.
[21] YAO Huaxu,ZHANG Chuxu,WEI Ying,et al.Graph few-shot learning via knowledge transfer[EB/OL].[2020-04-12].http://arxiv.org/abs/1910.03053v1.
[22] YAN Sijie,XIONG Yuanjun,LIN Dahua.Spatial temporal graph convolutional networks for skeleton-based action recognition[J].Journal of Electronic Imaging,2019,28(4):1-10.
[23] YOU Renchuan,GUO Zhiyao,CUI Lei,et al.Cross-modality attention with semantic graph embedding for multi-label classification[EB/OL].[2020-04-12].https://arxiv.org/abs/1912.07872v1.
[24] HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
[25] VELICKOVIC P,CUCURULL G,CASANOVA A,et al.Graph attention networks[EB/OL].[2020-04-12].https://arxiv.org/abs/1710.10903v3.
[26] TIAN Fei,GAO Bin,CUI Qing,et al.Learning deep representations for graph clustering[C]//Proceedings of the 28th AAAI Conference on Artificial Intelligence.Palo Alto,USA:AAAI Press,2014:1293-1299.
[27] HUANG Yujun,WENG Yunpeng,YU Shuai,et al.Diffusion convolutional recurrent neural network:data-driven traffic forecasting[C]//Proceedings of IEEE International Conference on Trust,Security and Privacy in Computing and Communications.Washington D.C.,USA:IEEE Press,2018:25-38.
[28] CAI H,ZHENG V W,CHANG K C C.A comprehensive survey of graph embedding:problems,techniques,and applications[J].IEEE Transactions on Knowledge and Data Engineering,2018,30(9):1616-1637.
[29] KIPF T N,MAX W.Semi-supervised classification with graph convolutional networks[EB/OL].[2020-04-12].https://arxiv.org/abs/1609.02907.
[30] HENAFF M,BRUNA J,LECUN Y.Deep convolutional networks on graph-structured data[EB/OL].[2020-04-12].https://arxiv.org/abs/1506.05163.
[31] ZHANG Xiongtong,LIU Han,LI Qimai,et al.Attributed graph clustering via adaptive graph convolution[EB/OL].[2020-04-12].https://arxiv.org/abs/1906.01210.
[32] SCARSELLI F,GORI M,TSOI A C,et al.The graph neural network model[J].IEEE Transactions on Neural Networks,2009,20(1):61-80.
[33] DAI H,KOZAREVA Z,DAI B,et al.Learning steady-states of iterative algorithms over graphs[C]//Proceedings of International Conference on Machine Learning.Washington D.C.,USA:IEEE Press,2018:1114-1122.
[34] ATWOOD J,TOWSLEY D.Diffusion-convolutional neural networks[C]//Proceedings of Advances in Neural Information Processing Systems.Washington D.C.,USA:IEEE Press,2016:1993-2001.
[35] ZHUANG Chenyi,MA Qiang.Dual graph convolutional networks for graph-based semi-supervised classifica-tion[C]//Proceedings of 2018 Conference on World Wide Web.New York,USA:ACM Press,2018:499-508.
[36] HAMILTON W,YING Z,LESKOVEC J.Inductive representation learning on large graphs[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.New York,USA:ACM Press,2017:1024-1034.
[37] GILMER J,SCHOENHOLZ S S,RILEY P F,et al.Neural message passing for quantum chemistry[C]//Proceedings of International Conference on Machine Learning.New York,USA:ACM Press,2017:1263-1272.
[38] LI Ruoyu,WANG Sheng,ZHU Feiyun,et al.Adaptive graph convolutional neural networks[C]//Proceedings of AAAI Conference on Artificial Intelligence.Palo Alto,USA:AAAI Press,2018:3546-3553.
[39] KEARNES S,MCCLOSKEY K.BERNDL M,et al.Molecular graph convolutions:moving beyond finger-prints[J].Journal of Computer-Aided Molecular Design,2016,30(8):595-608.
[40] YING R,HE R,CHEN K,et al.Graph convolutional neural networks for Web-scale recommender systems[EB/OL].[2020-04-12].https://arxiv.org/abs/1806.01973.
[41] CHEN Jie,MA Tengfei,XIAO Cao.FastGCN:fast learning with graph convolutional networks via importance sampling[EB/OL].[2020-04-12].https://arxiv.org/abs/1801.10247.
[42] ABU-EL-HAIJA S,PEROZZI B,KAPOOR A,et al.MixHop:higher-order graph convolutional architectures via sparsified neighborhood mixing[EB/OL].[2020-04-12].https://arxiv.org/abs/1905.00067.
[43] LI Y,TARLOW D,BROCKSCHMIDT M,et al.Gated graph sequence neural networks[EB/OL].[2020-04-12].https://arxiv.org/abs/1511.05493.
[44] TAI K S,SOCHER R,MANNING C D.Improved semantic representations from tree-structured long short-term memory networks[C]//Proceedings of IJCNLP'15.New York,USA:ACM Press,2015:1556-1566.
[45] YOU J,YING R,REN X,et al.GraphRNN:generating realistic graphs with deep auto-regressive models[C]//Proceedings of International Conference on Machine Learning.New York,USA:ACM Press,2018:5694-5703.
[46] PENG N,POON H,QUIRK C,et al.Cross-sentence N-ary relation extraction with graph LSTMs[J].Transactions of the Association for Computational Linguistics,2017,5:101-115.
[47] MA Yao,GUO Ziyi,REN Zhaochun,et al.Dynamic graph neural networks[EB/OL].[2020-04-12].https://arxiv.org/abs/1810.10627?context=stat.
[48] CHOI E,BAHADORI M T,SONG L,et al.GRAM:graph-based attention model for healthcare representation learning[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:ACM Press,2017:787-795.
[49] ZHANG Jiani,SHI Xingjian,XIE Junyuan,et al.GaAN:gated attention networks for learning on large and spatiotemporal graphs[EB/OL].[2020-04-12].https://arxiv.org/abs/1803.07294.
[50] LEE J B,ROSSI R,KONG X.Graph classification using structural attention[C]//Proceedings of ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.New York,USA:ACM Press,2018:1666-1674.
[51] SHI Chuan,LI Yitong,ZHANG Jiawei,et al.A survey of heterogeneous information network analysis[J].IEEE Transactions on Knowledge and Data Engineering,2019,29(1):17-37.
[52] WANG Xiao,JI Houye,SHI Chuan,et al.Heterogeneous graph attention network[C]//Proceedings of 2019 World Wide Web Conference.New York,USA:ACM Press,2019:2022-2032.
[53] YANG Sibei,LI Guanbin,YU Yizhou.Dynamic graph attention for referring expression comprehension[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2019:4643-4652.
[54] HA J W,PYO H,KIM J H.Large-scale item categorization in e-commerce using multiple recurrent neural networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:ACM Press,2016:1225-1234.
[55] WANG Daixin,CUI Peng,ZHU Wenwu.Structural deep network embedding[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:ACM Press,2016:1225-1234.
[56] KIPF T N,WELLING M.Variational graph auto-encoders[EB/OL].[2020-04-12].https://arxiv.org/abs/1611.07308.
[57] ZHU Dingyuan,CUI Peng,WANG Daixin,et al.Deep variational network embedding in Wasserstein space[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.New York,USA:ACM Press,2018:2827-2836.
[58] YU Bin,YIN Haoteng,ZHU Zhanxing.Spatio-temporal graph convolutional networks:a deep learning framework for traffic forecasting[C]//Proceedings of International Joint Conference on Artificial Intelligence.New York,USA:ACM Press,2018:3634-3640.
[59] SIMONYAN K,ZISSERMAN A.Two-stream convolu-tional networks for action recognition in videos[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems.New York,USA:ACM Press,2014:568-576.
[60] YAN Sijie,XIONG Yuanjun,LIN Dahua.Spatial temporal graph convolutional networks for skeleton-based action recognition[EB/OL].[2020-04-12].https://arxiv.org/abs/1801.07455.
[61] PEROZZI B,AL-RFOU R,SKIENA S.DeepWalk:online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:ACM Press,2014:701-710.
[62] ABU-EL-HAIJA S,PEROZZI B,AL-RFOU R,et al.Watch your step:learning node embeddings via graph attention[C]//Proceedings of Advances in Neural Information Processing Systems.Washington D.C.,USA:IEEE Press,2018:9197-9207.
[63] CHEN Shizhe,ZHAO Yida,JIN Qin,et al.Fine-grained video-text retrieval with hierarchical graph reasoning[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2020:1-10.
[64] DAI Hanjun,TIAN Yingtao,DAI Bo,et al.Syntax-directed variational autoencoder for molecule generation[EB/OL].[2020-04-12].http://www.quantum-machine.org/workshops/nips2017/assets/pdf/sdvae_workshop_camera_ready.pdf.
[65] GOMEZ-BOMBARELLI R,Jennifer N.Automatic chemical design using a data-driven continuous representa-tion of molecules[J].ACS Central Science,2018,4(2):268-276.
[66] CHEN Bo,SUN Le,HAN Xianpei.Sequence-to-action:end-to-end semantic graph generation for semantic parsing[C]//Proceedings of Annual Meeting of the Association for Computational Linguistics.Philadelphia,USA:ACL Press,2018:766-777.
[67] JOHNSON D D.Learning graphical state transitions[EB/OL].[2020-04-12].https://openreview.net/pdf?id=HJ0NvFz xl.
[68] LI Y,VINYALS O,DYER C,et al.Learning deep generative models of graphs[EB/OL].[2020-04-12].https://arxiv.org/abs/1803.03324.
[69] CAO N D,KIPF T.MolGAN:an implicit generative model for small molecular graphs[EB/OL].[2020-04-12].https://arxiv.org/abs/1805.11973.
[70] DIXIT A K,SHERRERD J J.Optimization in economic theory[M].Cambridge,USA:Oxford University Press,1990.
[71] LIAO P,ZHAO H,XU K,et al.Graph adversarial networks:protecting information against adversarial attacks[EB/OL].[2020-04-12].http://arxiv.org/abs/2009.13504.
[72] AKOGLU L,TONG H,KOUTRA D.Graph based anomaly detection and description:a survey[J].Data Mining and Knowledge Discovery,2015,29(3):626-688.
[73] OTTERLO M V,WIERING M.Reinforcement learning and Markov decision processes[M].Berlin,Germany:Springer,2012.
[74] DONNAT C,ZITNIK M,HALLAC D,et al.Learning structural node embeddings via diffusion wavelets[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:ACM Press,2018:1320-1329.
[75] MADJIHEUREM S,TONI L.Representation learning on graphs:a reinforcement learning application[EB/OL].[2020-04-12].https://arxiv.org/abs/1901.05351v1.
[76] SRIDHAR M.Representation policy iteration[C]//Proceedings of the 21st Conference on Uncertainty in Artificial Intelligence.Palo Alto,USA:AAAI Press,2005:372-379.
[77] BOSCAINI D,MASCI J,MELZI S,et al.Learning class-specific descriptors for deformable shapes using localized spectral convolutional networks[J].Computer Graphics Forum,2015,34:13-23.
[78] LEE J,KIM H,LEE J,et al.Transfer learning for deep learning on graph-structured data[C]//Proceedings of the 31st AAAI Conference on Artificial Intelligence.New York,USA:ACM Press,2017:2154-2160.
[79] PAN S J,YANG Q.A survey on transfer learning[J].IEEE Transactions on Knowledge and Data Engineering,2010,22(10):1345-1359.
[80] DICK R P,RHODES D L,WOLF W.TGFF:task graphs for free[C]//Proceedings of the 6th International Workshop on Hardware/Software Codesign.Washington D.C.,USA:IEEE Press,1998:1-5.
[81] HUANG D,NAIR S,XU D,et al.Neural task graphs:generalizing to unseen tasks from a single video demonstration[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2019:8557-8566.
[82] WANG X,YE Y,GUPTA A.Zero-shot recognition via semantic embeddings and knowledge graphs[C]//Proceed-ings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2018:6857-6866.
[83] LEE C,FANG W,YEH C,et al.Multi-label zero-shot learning with structured knowledge graphs[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2018:1576-1585.
[84] BOJCHEVSKI A,SHCHUR O,UGNER D Z,et al.NetGAN:generating graphs via random walks[EB/OL].[2020-04-12].https://arxiv.org/abs/1803.00816.
[85] ZHANG Yue,LIU Qi,SONG Linfeng.Sentence-state LSTM for text representation[EB/OL].[2020-04-12].http://export.arxiv.org/abs/1805.02474.
[86] XU D,ZHU Y,CHOY C B,et al.Scene graph generation by iterative message passing[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:5410-5419.
[87] HU R,ROHRBACH A,DARRELL T,et al.Language-conditioned graph networks for relational reasoning[C]//Proceedings of IEEE/CVF International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2019:10293-10302.
[88] WANG Haofen,DING Jun,HU Fanghuai,et al.Survey on large scale enterprise-level knowledge graph practices[J].Computer Engineering,2020,46(7):1-13.(in Chinese)王昊奋,丁军,胡芳槐,等.大规模企业级知识图谱实践综述[J].计算机工程,2020,46(7):1-13.
[89] ULUTAN O,IFTEKHAR A S M,MANJUNATH B S.VSGNet:spatial attention network for detecting human object interactions using graph convolutions[EB/OL].[2020-04-12].https://arxiv.org/abs/2003.05541.

选择文件类型/文献管理软件名称

选择包含的内容