基于图卷积网络和自编码器的半监督网络表示学习模型  

Semi-supervised Network Representation Learning Model Based on Graph Convolutional Networks and Auto Encoder

作　　者：王杰[1] 张曦煌[1] WANG Jie;ZHANG Xihuang(School of Internet of Things Engineering,Jiangnan University,Wuxi 214122)

机构地区：[1]江南大学物联网工程学院

出　　处：《模式识别与人工智能》2019年第4期317-325,共9页Pattern Recognition and Artificial Intelligence

基　　金：江苏省产学研合作基金项目(No.BY2015019-30)资助~~

摘　　要：为了保留网络结构信息和节点特征信息,结合图卷积神经网络(GCN)和自编码器(AE),提出可扩展的半监督深度网络表示学习模型(Semi-GCNAE)。利用GCN捕获节点的K阶邻域中所有节点的结构和特征信息,并将捕获的信息作为AE的输入。AE对GCN捕获的K阶邻域信息进行特征提取和非线性降维,并结合Laplacian特征映射保留节点的团簇结构信息。引入集成学习方法联合训练GCN和AE,使模型习得的节点低维向量表示能同时保留网络结构信息和节点特征信息。在5个真实数据集上的广泛评估表明,文中模型习得的节点低维向量表示可以有效保留网络的结构和节点特征信息,并在节点分类、可视化和网络重构任务上性能较优。Combining graph convolutional networks(GCN) and auto encoder(AE),a scalable semi- supervised network representation learning model,Semi-GCNAE,is proposed to preserve the network structure information and node feature information.GCN is utilized to capture the structure and feature information of all nodes in K-order neighborhood of the node.The captured information is utilized as the input of AE.The K-order neighborhood information captured by GCN is extracted and the dimension is reduced nonlinearly by AE.The cluster structure information of nodes is preserved by combining Laplacian feature mapping.The ensemble learning method is introduced to train GCN and AE jointly.Therefore,the learned low-dimensional vector representation of nodes can retain both network structure information and node feature information.Extensive evaluation on five real datasets shows that the low- dimensional vector representation of nodes acquired by the proposed model preserves the structure and characteristics of the network effectively.And it generates better performance in node classification,visualization and network reconstruction tasks.

关 键 词：网络表示学习 图卷积神经网络(GCN) 自编码器(AE) LAPLACIAN 特征映射 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]