计算机科学 ›› 2020, Vol. 47 ›› Issue (9): 219-225.doi: 10.11896/jsjkx.190900044

• 人工智能 • 上一篇    下一篇

基于深度图卷积胶囊网络的图分类模型

刘海潮1, 王莉2   

  1. 1 太原理工大学软件学院 太原030600
    2 太原理工大学大数据学院 太原030600
  • 收稿日期:2019-09-05 发布日期:2020-09-10
  • 通讯作者: 王莉(wangli@tyut.edu.cn)
  • 作者简介:liuhaichao1028@link.tyut.edu.cn
  • 基金资助:
    国家自然科学基金(61872260);山西省重点研发计划国际合作项目(201703D421013)

Graph Classification Model Based on Capsule Deep Graph Convolutional Neural Network

LIU Hai-chao1, WANG Li2   

  1. 1 College of Software,Taiyuan University of Technology,Taiyuan 030600,China
    2 College of Data Science,Taiyuan University of Technology,Taiyuan 030600,China
  • Received:2019-09-05 Published:2020-09-10
  • About author:LIU Hai-chao,born in 1995,postgra-duate.His main research interests include machine learning,and graph neural network.
    WANG Li,born in 1971,professor,Ph.Dsupervisor,is a member of China Computer Federation.Her main research interests include big data calculation,data mining,and social computing.
  • Supported by:
    National Natural Science Foundation of China (61872260) and Key Research and Development Program International Cooperation Project of Shanxi Province of China (201703D421013).

摘要: 针对提取图表征用于图分类过程中的结构信息提取过程的问题,提出了一种图卷积神经网络与胶囊网络融合的图分类模型。首先,利用图卷积神经网络处理图中的节点信息,迭代以后得到节点表征,表征中蕴含着该节点的子树结构信息;然后,利用Weisfeiler-Lehman图核算法的思想对节点表征的多维度进行排序,得到多视角的图表征;最后,将多视角的图表征整理成胶囊的形式并输入胶囊网络,使用动态路由算法得到更高层次的分类胶囊,进而进行分类。实验结果表明,所提模型在公共数据集上的分类准确度提升了1%~3%,同时具备更强的结构特征提取能力,在少样本情况下的表现比DGCNN更加稳定。

关键词: Weisfeiler-Lehman图核算法, 胶囊网络, 图表征, 图分类, 图卷积神经网络

Abstract: Aiming at the problems of structure information extraction when the extracted graph representation is used for graph classification,a graph classification model based on the fusion of graph convolutional neural network and capsule network is proposed.Firstly,the node information in the graph is processed by the convolutional neural network,and the node representation is obtained after iteration.The sub-tree structure information of the node is contained in the representation.Then,by using the idea of Weisfeiler-Lehman algorithm,the multi-dimensional representations of nodes are sorted to obtain multi-view representations of the graph.Finally,the multi-view graph representations are converted into capsules and input into the capsule network to obtain a higher level of classification capsule by dynamic routing algorithm,then proceed to classification.The experimental results show that the classification accuracy of the proposed model is improved by 1%~3% on the public dataset,and it has stronger structu-ral feature extraction ability.Compared with DGCNN,its performance is more stable in the case of less samples.

Key words: Capsule network, Graph classification, Graph convolutional neural network, Graph representation, Weisfeiler-Lehman graph kernel algorithm

中图分类号: 

  • TP301.6
[1] SCARSELLI F,GORI M,TSOI A C,et al.The graph neuralnetwork model[J].IEEE Transactions on Neural Networks,2009,20(1):61-80.
[2] BRUNA J,ZAREMBA W,SZLAMA,et al.Spectral networksand locally connected networks on graphs[J].arXiv:1312.6203,2013.
[3] DEFFERRARD M,BRESSON X,VANDERGHEYNST P.Con-volutional neural networks on graphs with fast localized spectral filtering[C]//Advances in Neural Information Processing Systems.2016:3844-3852.
[4] KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks[J].arXiv:1609.02907,2016.
[5] DUVENAUD D K,MACLAURIN D,IPARRAGUIRRE J,et al.Convolutional networks on graphs for learning molecular fingerprints[C]//Advances in Neural Information Processing Systems.2015:2224-2232.
[6] NIEPERT M,AHMED M,KUTZKOV K.Learning convolu-tional neural networks for graphs[C]//International Conference on Machine Learning.2016:2014-2023.
[7] ZHANG M,CUI Z,NEUMANNM,et al.An end-to-end deep learning architecture for graph classification[C]//Thirty-Se-cond AAAI Conference on Artificial Intelligence.2018.
[8] SABOUR S,FROSST N,HINTONG E.Dynamic routing be-tween capsules[C]//Advances in Neural Information Proces-sing Systems.2017:3856-3866.
[9] BAI L,XU L X,CUI L X,et al.Graph kernel in machine learning:recent works and future developments[J].Journal of Anhui University (Natural Science Edition),2017,41(1):21-28.
[10] HAUSSLER D.Convolution kernels on discrete structures[R].Technical Report UCS-CRL-99-10,UC Santa Cruz,1999.
[11] GÄRTNER T,FLACH P,WROBEL S.On graph kernels:Hardness results and efficient alternatives[M]//Learning Theo-ry and Kernel Machines.Berlin:Springer,2003:129-143.
[12] BORGWARDT K M,KRIEGEL H P.Shortest-path kernels on graphs[C]//Fifth IEEE International Conference on Data Mi-ning (ICDM’05).IEEE,2005.
[13] SHERVASHIDZE N,SCHWEITZER P,LEEUWEN E J,et al.Weisfeiler-lehman graph kernels[J].Journal of Machine Lear-ning Research,2011,12(Sep):2539-2561.
[14] YING Z,YOU J,MORRISC,et al.Hierarchical graph represen-tation learning with differentiable pooling[C]//Advances in Neural Information Processing Systems.2018:4805-4815.
[15] LEE J B,ROSSI R,KONG X.Graph classification using structural attention[C]//Proceedings of the 24th ACM SIGKDD International Conference on KnoWeisfeiler-Lehmanedge Discovery & Data Mining.ACM,2018:1666-1674.
[16] VERMA S,ZHANG Z L.Graph capsule convolutional neural networks[J].arXiv:1805.08090,2018.
[17] GAO H Y,WANG Z Y,JI S W.Large-scale learnable graphconvolutional networks[C]//Proceedings of the 24th ACM SIGKDD International Conference on KnoWeisfeiler-Lehmanedge Discovery & Data Mining.ACM,2018.
[18] ZHOU J,CUI G,ZHANG Z,et al.Graph neural networks:A review of methods and applications[J].arXiv:1812.08434,2018.
[19] SHERVASHIDZE N,VISHWANATHAN S,PETRI T,et al.Efficient graphlet kernels for large graph comparison[C]//AISTATS.2009:488-495.
[20] ATWOOD J,TOWSLEY D.Diffusion-convolutional neural networks[C]//Advances in Neural Information Processing Systems.2016:1993-2001.
[1] 李宗民, 张玉鹏, 刘玉杰, 李华.
基于可变形图卷积的点云表征学习
Deformable Graph Convolutional Networks Based Point Cloud Representation Learning
计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023
[2] 檀莹莹, 王俊丽, 张超波.
基于图卷积神经网络的文本分类方法研究综述
Review of Text Classification Methods Based on Graph Convolutional Network
计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064
[3] 武霖, 孙静宇.
多分支RA胶囊网络及在图像分类中的应用
Multi-branch RA Capsule Network and Its Application in Image Classification
计算机科学, 2022, 49(6): 224-230. https://doi.org/10.11896/jsjkx.210400087
[4] 李子仪, 周夏冰, 王中卿, 张民.
基于用户关联的立场检测
Stance Detection Based on User Connection
计算机科学, 2022, 49(5): 221-226. https://doi.org/10.11896/jsjkx.210400135
[5] 高越, 傅湘玲, 欧阳天雄, 陈松龄, 闫晨巍.
基于时空自适应图卷积神经网络的脑电信号情绪识别
EEG Emotion Recognition Based on Spatiotemporal Self-Adaptive Graph ConvolutionalNeural Network
计算机科学, 2022, 49(4): 30-36. https://doi.org/10.11896/jsjkx.210900200
[6] 李浩, 张兰, 杨兵, 杨海潇, 寇勇奇, 王飞, 康雁.
融合双重权重机制和图卷积神经网络的微博细粒度情感分类
Fine-grained Sentiment Classification of Chinese Microblogs Combining Dual Weight Mechanismand Graph Convolutional Neural Network
计算机科学, 2022, 49(3): 246-254. https://doi.org/10.11896/jsjkx.201200073
[7] 苗启广, 辛文天, 刘如意, 谢琨, 王泉, 杨宗凯.
面向智慧教育行为分析的图卷积骨架动作识别方法
Graph Convolutional Skeleton-based Action Recognition Method for Intelligent Behavior Analysis
计算机科学, 2022, 49(2): 156-161. https://doi.org/10.11896/jsjkx.220100061
[8] 张虎, 柏萍.
融入句子中远距离词语依赖的图卷积短文本分类方法
Graph Convolutional Networks with Long-distance Words Dependency in Sentences for Short Text Classification
计算机科学, 2022, 49(2): 279-284. https://doi.org/10.11896/jsjkx.201200062
[9] 张玮琪, 汤轶丰, 李林燕, 胡伏原.
基于场景图的段落生成序列图像方法
Image Stream From Paragraph Method Based on Scene Graph
计算机科学, 2022, 49(1): 233-240. https://doi.org/10.11896/jsjkx.201100207
[10] 范红杰, 李雪冬, 叶松涛.
面向电子病历语义解析的疾病辅助诊断方法
Aided Disease Diagnosis Method for EMR Semantic Analysis
计算机科学, 2022, 49(1): 153-158. https://doi.org/10.11896/jsjkx.201100125
[11] 陈志文, 王坤, 周广蕴, 王旭, 张晓丹, 朱虎明.
基于胶囊网络及其权重剪枝的SAR图像变化检测方法
SAR Image Change Detection Method Based on Capsule Network with Weight Pruning
计算机科学, 2021, 48(7): 190-198. https://doi.org/10.11896/jsjkx.200800225
[12] 梁浩宏, 古天龙, 宾辰忠, 常亮.
联合学习用户端和项目端知识图谱的个性化推荐
Combining User-end and Item-end Knowledge Graph Learning for Personalized Recommendation
计算机科学, 2021, 48(5): 109-116. https://doi.org/10.11896/jsjkx.200600115
[13] 王文博, 罗恒利.
基于图卷积神经网络的完全图人脸聚类
Complete Graph Face Clustering Based on Graph Convolution Network
计算机科学, 2021, 48(11A): 275-277. https://doi.org/10.11896/jsjkx.201200102
[14] 康雁, 谢思宇, 王飞, 寇勇奇, 徐玉龙, 吴志伟, 李浩.
基于双路信息时空图卷积网络的交通预测模型
Traffic Prediction Model Based on Dual Path Information Spatial-Temporal Graph Convolutional Network
计算机科学, 2021, 48(11A): 46-51. https://doi.org/10.11896/jsjkx.201200184
[15] 高创, 李建华, 季秀怡, 朱程龙, 李诗良, 李洪林.
基于图卷积神经网络的药物靶标作用关系预测方法
Drug Target Interaction Prediction Method Based on Graph Convolutional Neural Network
计算机科学, 2021, 48(10): 127-134. https://doi.org/10.11896/jsjkx.200700068
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!