面向节点分类任务的节点级自适应图卷积神经网络

doi:10.16451/j.cnki.issn1003-6059.202404001

摘要
图/表
参考文献
相关文章 (5)

全文: PDF (1038 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要图神经网络通过对图中节点的递归采样与聚合以学习节点嵌入,而现有方法中节点采样与聚合的模式较固定,对局部模式的多样性捕获存在不足,从而降低模型性能.因此,文中提出节点级自适应图卷积神经网络(Node-Level Adaptive Graph Convolutional Neural Network, NA-GCN).设计基于节点重要性的采样策略,自适应地确定各节点的邻域规模.同时,提出基于自注意力机制的聚合策略,自适应地融合给定邻域内的节点信息.在多个基准图数据集上的实验表明,NA-GCN在节点分类任务上具有较优性能.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	王鑫隆
	胡睿
	郭亚梁
	杜航原
	张槟淇
	王文剑

关键词 ：自适应采样, 自适应聚合, 节点分类, 图神经网络(GNNs), 谱图理论

Abstract：Graph neural networks learn node embeddings by recursively sampling and aggregating information from nodes in a graph. However, the relatively fixed pattern of existing methods in node sampling and aggregation results in inadequate capture of local pattern diversity, thereby degrading the performance of the model. To solve this problem, a node-level adaptive graph convolutional neural network(NA-GCN) is proposed. A sampling strategy based on node importance is designed to adaptively determine the neighborhood size of each node. An aggregation strategy based on the self-attention mechanism is presented to adaptively fuse the node information within a given neighborhood. Experimental results on multiple benchmark graph datasets show the superiority of NA-GCN in node classification tasks.

Key words： Adaptive Sampling Adaptive Aggregation Node Classification Graph Neural Networks(GNNs) Spectral Graph Theory

收稿日期: 2024-01-09

ZTFLH:

TP 391

基金资助:国家自然科学基金项目(No.U21A20513,62076154)、山西省重点研发计划项目(No.202202020101003,202302010101007)、山西省基础研究计划项目(No.202303021221055)资助

通讯作者: 王文剑,博士,教授,主要研究方向为机器学习、数据挖掘、计算智能.E-mail:wjwang@sxu.edu.cn.

作者简介: 王鑫隆,硕士研究生,主要研究方向为机器学习、图神经网络.E-mail:1757239635@qq.com.胡睿,博士研究生,主要研究方向为图表示学习、点云数据分析.E-mail:rynehu@outlook.com.郭亚梁,硕士研究生,主要研究方向为机器学习、图神经网络.E-mail:591180224@qq.com. 杜航原,博士,副教授,主要研究方向为图表示学习.E-mail:duhangyuan@sxu.edu.cn.张槟淇,硕士,讲师,主要研究方向为机器学习、数据挖掘.E-mail:843545395@qq.com.

引用本文:

王鑫隆, 胡睿, 郭亚梁, 杜航原, 张槟淇, 王文剑. 面向节点分类任务的节点级自适应图卷积神经网络[J]. 模式识别与人工智能, 2024, 37(4): 287-298. WANG Xinlong, HU Rui, GUO Yaliang, DU Hangyuan, ZHANG Binqi, WANG Wenjian. Node-Level Adaptive Graph Convolutional Neural Network for Node Classification Tasks. Pattern Recognition and Artificial Intelligence, 2024, 37(4): 287-298.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202404001 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2024/V37/I4/287

[1] NEWMAN M E J, GIRVAN M. Finding and Evaluating Community Structure in Networks. Physical Review E, 2004, 69. DOI: 10.1103/PhysRevE.69.026113.
[2] KROGAN N J, CAGNEY G, YU H Y, et al. Global Landscape of Protein Complexes in the Yeast Saccharomyces Cerevisiae. Nature, 2006, 440(7084): 637-643.
[3] LUO X L, ZHU C J, ZHANG D T, et al. STG4Traffic: A Survey and Benchmark of Spatial-Temporal Graph Neural Networks for Tra-ffic Prediction[C/OL].[2023-12-02]. https://arxiv.org/pdf/2307.00495.pdf.
[4] WU Z H, PAN S R, CHEN F W, et al. A Comprehensive Survey on Graph Neural Networks. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(1): 4-24.
[5] 肖国庆,李雪琪,陈玥丹,等.大规模图神经网络研究综述.计算机学报, 2024, 47(1): 148-171.
(XIAO G Q, LI X Q, CHEN Y D, et al. A Survey of Large-Scale Graph Neural Networks. Chinese Journal of Computers, 2024, 47(1): 148-171.)
[6] 谢娟英,张建宇.图卷积神经网络综述.陕西师范大学学报(自然科学版), 2024, 52(2): 89-101.
(XIE J Y, ZHANG J Y. The Review of the Graph Convolutional Neural Networks. Journal of Shaanxi Normal University(Natural Science Edition), 2024, 52(2): 89-101.)
[7] DU H Y, YU R, BAI L, et al. Learning Structure Perception MLPs on Graphs: A Layer-Wise Graph Knowledge Distillation Framework. International Journal of Machine Learning and Cybernetics, 2024. DOI: 10.1007/s13042-024-02150-2.
[8] ZHU X J, GHAHRAMANI Z, LAFFERTY J D. Semi-supervised Learning Using Gaussian Fields and Harmonic Functions // Proc of the 20th International Conference on Machine Learning. San Diego, USA: JMLR, 2003: 912-919.
[9] BELKIN M, NIYOGI P, SINDHWANI V. Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples. Journal of Machine Learning Research, 2006, 7: 2399-2434.
[10] BRUNA J, ZAREMBA W, SZLAM A, et al. Spectral Networks and Locally Connected Networks on Graphs[C/OL]. [2023-12-02]. https://arxiv.org/pdf/1312.6203.pdf.
[11] DEFFERRARD M, BRESSON X, VANDERGHEYNST P. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering // Proc of the 30th International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2016: 3844-3852.
[12] KIPF T N, WELLING M. Semi-supervised Classification with Graph Convolutional Networks[C/OL]. [2013-12-02]. https://arxiv.org/pdf/1609.02907.pdf.
[13] WU F, SOUZA A, ZHANG T Y, et al. Simplifying Graph Convolutional Networks. Proceedings of Machine Learning Research, 2019, 97: 6861-6871.
[14] 曾菊香,王平辉,丁益东,等.面向节点分类的图神经网络节点嵌入增强模型.浙江大学学报(工学版), 2023, 57(2): 219-225.
(ZENG J X, WANG P H, DING Y D, et al. Graph Neural Network Based Node Embedding Enhancement Model for Node Classification. Journal of Zhejiang University(Engineering Science), 2023, 57(2): 219-225.)
[15] LI Q M, HAN Z C, WU X M. Deeper Insights into Graph Convolutional Networks for Semi-supervised Learning // Proc of the 32nd AAAI Conference on Artificial Intelligence and 30th Innovative App-lications of Artificial Intelligence Conference and 8th AAAI Symposium on Educational Advances in Artificial Intelligence. Palo Alto, USA: AAAI Press, 2018: 3538-3545.
[16] RONG Y, HUANG W B, XU T Y, et al. DropEdge: Towards Deep Graph Convolutional Networks on Node Classification[C/OL].[2023-12-02]. https://arxiv.org/pdf/1907.10903.pdf.
[17] XU K Y L, LI C T, TIAN Y L, et al. Representation Learning on Graphs with Jumping Knowledge Networks. Proceedings of Machine Learning Research, 2018, 80: 5453-5462.
[18] CHEN M, WEI Z W, HUANG Z F, et al. Simple and Deep Graph Convolutional Networks // Proc of the 37th International Confe-rence on Machine Learning. San Diego, USA: JMLR, 2020: 1725-1735.
[19] LI G H, MULLER M, THABET A, et al. DeepGCNs: Can GCNs Go as Deep as CNNs? // Proc of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2019: 9266-9275.
[20] LI R Y, WANG S, ZHU F Y, et al. Adaptive Graph Convolutional Neural Networks // Proc of the 32nd AAAI Conference on Artificial Intelligence and 30th Innovative Applications of Artificial Intelligence Conference and 8th AAAI Symposium on Educational Advances in Artificial Intelligence. Palo Alto, USA: AAAI Press, 2018: 3546-3553.
[21] XU K Y L, HU W H, LESKOVEC J, et al. How Powerful Are Graph Neural Networks?[C/OL]. [2023-12-02]. https://arxiv.org/pdf/1810.00826.pdf.
[22] VELIČKOVIĆ P, CUCURULL G, CASANOVA A, et al. Graph Attention Networks[C/OL].[2023-12-02]. https://arxiv.org/pdf/1710.10903.
[23] HAMILTON W L, YING Z, LESKOVEC J. Inductive Representation Learning on Large Graphs // Proc of the 31st International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2017: 1025-1035.
[24] YING R, HE R N, CHEN K F, et al. Graph Convolutional Neural Networks for Web-Scale Recommender Systems // Proc of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2018: 974-983.
[25] 邹长宽,田小平,张晓燕,等.基于GraphSage节点度重要性聚合的网络节点分类研究.科学技术与工程, 2022, 22(32): 14306-14312.
(ZOU C K, TIAN X P, ZHANG X Y, et al. Research on Network Node Classification Based on GraphSage Node Degree Importance Aggregation. Science Technology and Engineering, 2022, 22(32): 14306-14312.)
[26] CHEN J F, ZHU J, SONG L. Stochastic Training of Graph Convolutional Networks with Variance Reduction. Proceedings of Machine Learning Research, 2018, 80: 942-950.
[27] CHEN J, MA T F, XIAO C. FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling[C/OL]. [2023-12-02]. https://openreview.net/pdf?id=rytstxWAW.
[28] ZOU D F, HU Z N, WANG Y W, et al. Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks // Proc of the 33rd International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2019: 11249-11259.
[29] HUANG W B, ZHANG T, RONG Y, et al. Adaptive Sampling Towards Fast Graph Representation Learning // Proc of the 32nd International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2018: 4563-4572.
[30] CHIANG W L, LIU X Q, SI S, et al. Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks // Proc of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2019: 257-266.
[31] ZENG H Q, ZHOU H K, SRIVASTAVA A, et al. GraphSAINT: Graph Sampling Based Inductive Learning Method[C/OL].[2023-12-02]. https://arxiv.org/pdf/1907.04931.pdf.
[32] BAI J Y, REN Y X, ZHANG J W. Ripple Walk Training: A Subgraph-Based Training Framework for Large and Deep Graph Neural Network // Proc of the International Joint Conference on Neural Networks. Washington, USA: IEEE, 2021. DOI: 10.1109/IJCNN52387.2021.9533429.
[33] ZENG H Q, ZHANG M H, XIA Y L, et al. Decoupling the Depth and Scope of Graph Neural Networks[C/OL].[2023-12-02]. https://arxiv.org/pdf/2201.07858v1.
[34] CORSO G, CAVALLERI L, BEAINI D, et al. Principal Neighbourhood Aggregation for Graph Nets // Proc of the 34th International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2020: 13260-13271.
[35] PEROZZI B, AL-RFOU R, SKIENA S. DeepWalk: Online Lear-ning of Social Representations // Proc of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2014: 701-710.
[36] HU Y, YOU H X, WANG Z C, et al. Graph-MLP: Node Classification without Message Passing in Graph[C/OL].[2023-12-02]. https://arxiv.org/pdf/2106.04051.pdf.
[37] BRODY S, ALON U, YAHAV E. How Attentive Are Graph Attention Networks?[C/OL]. [2023-12-02]. https://arxiv.org/pdf/2105.14491.pdf.
[38] YANG Z L, COHEN W, SALAKHUDINOV R. Revisiting Semi-supervised Learning with Graph Embeddings. Proceedings of Machine Learning Research, 2016, 48: 40-48.