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

作者：

Highlights：

• 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.

摘要

•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.

论文关键词：Graph representation learning,Graph convolutional autoencoders,Graph filter

论文评审过程：Received 4 July 2020, Revised 24 October 2020, Accepted 28 July 2021, Available online 10 August 2021, Version of Record 19 August 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108215