计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (8): 118-126.doi: 10.11896/jsjkx.241000186

• 数据库&大数据&数据科学 • 上一篇    下一篇

随时间持续演化的流图神经网络

郭虎升1,2, 张旭飞1, 孙玉杰1, 王文剑1,2   

  1. 1 山西大学计算机与信息技术学院 太原 030006
    2 计算智能与中文信息处理教育部重点实验室(山西大学) 太原 030006
  • 收稿日期:2024-10-31 修回日期:2025-05-25 出版日期:2025-08-15 发布日期:2025-08-08
  • 通讯作者: 王文剑(wjwang@sxu.edu.cn)
  • 作者简介:(guohusheng@sxu.edu.cn)
  • 基金资助:
    国家自然科学基金(62276157,U21A20513,62476157,62076154,61503229);山西省重点研发计划(202202020101003)

Continuously Evolution Streaming Graph Neural Network

GUO Husheng1,2, ZHANG Xufei1, SUN Yujie1, WANG Wenjian1,2   

  1. 1 School of Computer and Information Technology,Shanxi University,Taiyuan 030006,China
    2 Key Laboratory of Computational Intelligence and Chinese Information Processing(Shanxi University),Taiyuan 030006,China
  • Received:2024-10-31 Revised:2025-05-25 Online:2025-08-15 Published:2025-08-08
  • About author:GUO Husheng,born in 1986,Ph.D,professor,Ph.D supervisor,is a senior member of CCF(No.49571S).His main research interests include machine learning,data mining and computational intelligence.
    WANG Wenjian,born in 1968.Ph.D,professor,Ph.D supervisor,is a outstanding member of CCF(No.16143D).Her main research interests include machine learning,data mining and computational intelligence.
  • Supported by:
    National Natural Science Foundation of China(62276157,U21A20513,62476157,62076154,61503229) and Key Research & Development Program of Shanxi Province(202202020101003).

PDF (PC)

15

摘要： 流图在现实应用中广泛存在,其节点特征和结构特征会随时间推移而动态变化。尽管图神经网络在静态图节点分类中表现卓越,但其难以直接应用于流图,流图的持续演化会导致信息滞后和遗漏问题,所以模型难以准确提取流图特征。针对上述挑战,提出了一种随时间持续演化的流图神经网络(Continuously Evolution Streaming Graph Neural Network,CESGNN),以解决流图节点分类问题。该方法首先通过持续更新的图卷积网络(Continuous Updates Graph Convolutional Network,CU-GCN)增量地更新参数,以适应流图节点特征的变化,缓解信息滞后问题,然后自适应扩展的图神经网络(Adaptive Deepening Graph Neural Network,AD-GNN)通过将聚合和更新操作解耦,以挖掘流图深层特征,从而缓解信息遗漏问题。CESGNN通过有机地融合原始特征、CU-GCN提取的浅层特征和AD-GNN提取的深层特征,获得更准确、全面的流图特征表示。实验结果表明,CESGNN模型对流图具有良好的适应性和稳定性,提高了流图节点分类的准确率。

关键词: 流图, 图神经网络, 增量更新, 聚合与更新解耦, 特征融合

Abstract: Streaming graphs are widely used in practical applications,and their node and structure characteristics change dynamically with time.Although Graph Neural Network(GNN) is excellent in static graph node classification,it is difficult to apply it directly to streaming graphs,because the continuous evolution of streaming graphs will lead to information lag and omission,it is difficult for models to accurately extract streaming graph features.To solve the above challenges,the Continuously Evolving Streaming Graph Neural Network(CESGNN) is proposed to solve the node classification problem of streaming graph.Firstly,the Continuous Updates Graph Convolutional Network(CU-GCN) incrementally updates parameters to adapt to changes in the node characteristics of the streaming graph to alleviate the information lag problem.Then the Adaptive Deepening Graph Neural Network(AD-GNN) alleviates the information omission problem by decoupling the aggregation and updates operations to dig deep features of the streaming graph.CESGNN organically combines the original features,the shallow features extracted by CU-GCN,and the deep features extracted by AD-GNN to obtain a more accurate and comprehensive representation of streaming graph features.The experimental results show that CESGNN model has good adaptability and stability of streaming graph,and improves the accuracy of node classification of streaming graph.

Key words: Streaming graphs, Graph Neural Networks, Incrementally updating, Decoupling aggregation and update, Feature fusion

中图分类号: 

  • TP183
[1]BRAMBILLA M,GASPARINI M.Brand community analysison social networks using graph representation learning[C]//Proceedings of the 34th ACM SIGAPP Symposium on Applied Computing.2019:2060-2069.
[2]ZHANG S,ZHOU D,YILDIRIM M Y,et al.Hidden:Hierarchical dense subgraph detection with application to financial fraud detection[C]//Proceedings of the 2017 SIAM International Conference on Data Mining.Society for Industrial and Applied Mathematics.2017:570-578.
[3]WANG X,MA Y,WANG Y,et al.Traffic flow prediction viaspatial temporal graph neural network[C]//Proceedings of the Web Conference 2020.2020:1082-1092.
[4]SCARSELLI F,GORI M,TSOI A C,et al.The graph neural network model[J].IEEE Transactions on Neural Networks,2008,20(1):61-80.
[5]MICHELI A.Neural network for graphs:A contextual con-structive approach[J].IEEE Transactions on Neural Networks,2009,20(3):498-511.
[6]MA S,LIU J W,ZUO X.Survey on Graph Neural Network[J].Journal of Computer Research and Development,2022,59(1):47-80.
[7]BHAGAT S,CORMODE G,MUTHUKRISHNAN S.Nodeclassification in social networks[J].Social Network Data Analytics,2011:115-148.
[8]JI S Y,WEI Y X,DAI Q H,et al.Efficient hypergraph neural network on million-level data[J].Scientia Sinica Informationis,2024,54(4):853-871.
[9]HASAN M A,ZAKI M J.A survey of link prediction in social networks[J].Social Network Data Analytics,2011:243-275.
[10]NI Q J,PENG W Q,ZHANG Z Z,et al.Spatial-Temporal Graph Neural Network for Traffic Flow Prediction Based on InformationEnhanced Transmission[J].Journal of Computer Research and Development,2022,59(2):282-293.
[11]GUO J Y,LI R H,ZHANG Y,et al.Graph neural networkbased anomaly detection in dynamic networks[J].Journal of Software,2020,31(3):748-762.
[12]HAMILTON W,YING Z,LESKOVEC J.Inductive representation learning on large graphs[C]//Processing of the Advances in Neural Information Processing Systems.2017:1025-1035.
[13]ZHOU J,CUI G,HU S,et al.Graph neural networks:A review of methods and applications[J].AI Open,2020,1:57-81.
[14]PEROZZI B,AL-RFOU R,SKIENA S.Deepwalk:Online lear-ning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2014:701-710.
[15]TANG J,QU M,WANG M,et al.Line:Large-scale information network embedding[C]//Proceedings of the 24th International Conference on World Wide Web.2015:1067-1077.
[16]GROVER A,LESKOVEC J.node2vec:Scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Dining.2016:855-864.
[17]RIBEIRO L F R,SAVERESE P H P,FIGUEIREDO D R.struc2vec:Learning node representations from structural identity[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2017:385-394.
[18]PEROZZI B,KULKARNI V,CHEN H,et al.Don't walk,skip! online learning of multi-scale network embeddings[C]//Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2017.2017:258-265.
[19]KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks[J].arXiv:1609.02907,2016.
[20]VELIČKOVIĆ P,CUCURULL G,CASANOVA A,et al.Graph attention networks[C]//Proceedings of the International Conference on Learning Representations.2018.
[21]XU K,HU W,LESKOVEC J,et al.How powerful are graphneural networks?[C]//Proceeding of the International Conference on Learning Representations.2019.
[22]SKARDING J,GABRYS B,MUSIAL K.Foundations and modeling of dynamic networks using dynamic graph neural networks:A survey[J].IEEE Access,2021,9:79143-79168.
[23]ZHOU L,YANG Y,REN X,et al.Dynamic network embedding by modeling triadic closure process[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2018:571-578.
[24]ZUO Y,LIU G,LIN H,et al.Embedding temporal network via neighborhood formation[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2018:2857-2866.
[25]GERS F A,SCHRAUDOLPH N N,SCHMIDHUBER J.Learning precise timing with LSTM recurrent networks[J].Journal of Machine Learning Research,2002,3(Aug):115-143.
[26]WANG J,JIN Y,SONG G,et al.EPNE:Evolutionary patternpreserving network embedding[C]//Proceedings of the 24th European Conference on Artificial Intelligence.2020.
[27]PAREJA A,DOMENICONI G,CHEN J,et al.Evolvegcn:Evolving graph convolutional networks for dynamic graphs[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:5363-5370.
[28]SANKAR A,WU Y,GOU L,et al.Dysat:Deep neural representation learning on dynamic graphs via self-attention networks[C]//Proceedings of the 13th International Conference on Web Search and Data Mining.2020:519-527.
[29]TRIVEDI R,FARAJTABAR M,BISWAL P,et al.Dyrep:Learning representations over dynamic graphs[C]//Proceedings of the International Conference on Learning Representations.2019.
[30]DENG S,RANGWALA H,NING Y.Learning dynamic context graphs for predicting social events[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Disco-very and Data Mining.2019:1007-1016.
[31]MA Y,GUO Z,REN Z,et al.Streaming graph neural networks[C]//Proceedings of the 43rd international ACM SIGIR Confe-rence on Research and Development in Information Retrieval.2020:719-728.
[32]YAN S,XIONG Y,LIN D.Spatial temporal graph convolutional networks for skeleton-based action recognition[C]//Procee-dings of the AAAI Conference on Artificial Intelligence.2018.
[33]LIU M,GAO H,JI S.Towards deeper graph neural networks[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2020:338-348.
[34]ZHANG T,LIAO B,YU J,et al.Benchmark testing and analysis of node classification tasks in graph neural networks [J].Computer Science,2024,51(4):132-150.
[35]GASTEIGER J,BOJCHEVSKI A,GÜNNEMANN S.Predictthen Propagate:Graph Neural Networks meet Personalized PageRank[C]//Proceedings of the International Conference on Learning Representations.2018.
[36]CHIANG W L,LIU X,SI S,et al.Cluster-gcn:An efficient algorithm for training deep and large graph convolutional networks[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2019:257-266.
[37]WU F,SOUZA A,ZHANG T,et al.Simplifying graph convolutional networks[C]//Proceedings of the International Confe-rence on Machine Learning.2019:6861-6871.
[38]DU J,ZHANG S H,WU G H,et al.Topology adaptive graph convolutional networks[J].arXiv:1710.10370,2017.
[39]WANG J,SONG G,WU Y,et al.Streaming Graph Neural Networks via Continual Learning[C]//Proceedings of the 29th ACM International Conference on Information & Knowledge Management(CIKM'20).2020:1515-1524.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发