Depth-based subgraph convolutional auto-encoder for network representation learning

PATTERN RECOGNITION

卷:90

Article

Zhang, Zhihong¹  Chen, Dongdong¹  Wang, Zeli²  Li, Heng²  Bai, Lu³  Hancock, Edwin R.⁴ 

[1] Xiamen Univ, Software Sch, Xiamen, Peoples R China

[2] Hong Kong Polytech Univ, Dept Bldg & Real Estate, Hong Kong, Peoples R China

[3] Cent Univ Finance & Econ, Sch Informat, Beijing, Peoples R China

[4] Univ York, Dept Comp Sci, York, N Yorkshire, England

关键词: Network representation learning;    Graph convolutional neural network;    Node classification;   

DOI  :  10.1016/j.patcog.2019.01.045

来源: Elsevier

【 摘 要 】

Network representation learning (NRL) aims to map vertices of a network into a low-dimensional space which preserves the network structure and its inherent properties. Most existing methods for network representation adopt shallow models which have relatively limited capacity to capture highly non-linear network structures, resulting in sub-optimal network representations. Therefore, it is nontrivial to explore how to effectively capture highly non-linear network structure and preserve the global and local structure in NRL. To solve this problem, in this paper we propose a new graph convolutional autoencoder architecture based on a depth-based representation of graph structure, referred to as the depth-based subgraph convolutional autoencoder (DS-CAE), which integrates both the global topological and local connectivity structures within a graph. Our idea is to first decompose a graph into a family of K-layer expansion subgraphs rooted at each vertex aimed at better capturing long-range vertex inter-dependencies. Then a set of convolution filters slide over the entire sets of subgraphs of a vertex to extract the local structural connectivity information. This is analogous to the standard convolution operation on grid data. In contrast to most existing models for unsupervised learning on graph-structured data, our model can capture highly non-linear structure by simultaneously integrating node features and network structure into network representation learning. This significantly improves the predictive performance on a number of benchmark datasets. (C) 2019 Elsevier Ltd. All rights reserved.

【 授权许可】

Free