Graph convolutional autoencoders with co-learning of graph structure and node attributes

•We propose a novel end-to-end graph autoencoders model for the attributed graph.•The proposed model can reconstruct both the graph structure and node attributes.•The graph encoder is a completely low-pass filter.•The graph decoder is a completely high-pass filter.•Show the effectiveness of the prop...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition Vol. 121; p. 108215
Main Authors: Wang, Jie, Liang, Jiye, Yao, Kaixuan, Liang, Jianqing, Wang, Dianhui
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.01.2022
Subjects:
Graph convolutional autoencoders
Graph filter
Graph representation learning
Graph representation learning
Graph filter
Graph convolutional autoencoders
ISSN:0031-3203, 1873-5142
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•We propose a novel end-to-end graph autoencoders model for the attributed graph.•The proposed model can reconstruct both the graph structure and node attributes.•The graph encoder is a completely low-pass filter.•The graph decoder is a completely high-pass filter.•Show the effectiveness of the proposed model. Recently, graph representation learning based on autoencoders has received much attention. However, these methods suffer from two limitations. First, most graph autoencoders ignore the reconstruction of either the graph structure or the node attributes, which often leads to a poor latent representation of the graph-structured data. Second, for existing graph autoencoders models, the encoder and decoder are mainly composed of an initial graph convolutional network (GCN) or its variants. These traditional GCN-based graph autoencoders more or less encounter the problem of incomplete filtering, which causes these models to be unstable in practical applications. To address the above issues, this paper proposes the Graph convolutional Autoencoders with co-learning of graph Structure and Node attributes (GASN) based on variational autoencoders. Specifically, the proposed GASN encodes and decodes the node attributes and graph structure comprehensively in the graph-structured data. Furthermore, we design a completely low-pass graph encoder and a high-pass graph decoder. The experimental results on real-world datasets demonstrate that the proposed GASN achieves state-of-the-art performance on node clustering, link prediction, and visualization tasks.
ISSN:0031-3203
1873-5142
DOI:10.1016/j.patcog.2021.108215