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。
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.
作者
刘海潮
王莉
LIU Hai-chao;WANG Li(College of Software,Taiyuan University of Technology,Taiyuan 030600,China;College of Data Science,Taiyuan University of Technology,Taiyuan 030600,China)
出处
《计算机科学》
CSCD
北大核心
2020年第9期219-225,共7页
Computer Science
基金
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)。
