Beyond Low-pass Filtering: Graph Convolutional Networks with Automatic Filtering

• URL: http://arxiv.org/abs/2107.04755v1
• Date: Sat, 10 Jul 2021 04:11:25 GMT
• Title: Beyond Low-pass Filtering: Graph Convolutional Networks with Automatic Filtering
• Authors: Zonghan Wu, Shirui Pan, Guodong Long, Jing Jiang, Chengqi Zhang
• Abstract summary: We propose Automatic Graph Convolutional Networks (AutoGCN) to capture the full spectrum of graph signals. While it is based on graph spectral theory, our AutoGCN is also localized in space and has a spatial form.
• Score: 61.315598419655224
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Graph convolutional networks are becoming indispensable for deep learning from graph-structured data. Most of the existing graph convolutional networks share two big shortcomings. First, they are essentially low-pass filters, thus the potentially useful middle and high frequency band of graph signals are ignored. Second, the bandwidth of existing graph convolutional filters is fixed. Parameters of a graph convolutional filter only transform the graph inputs without changing the curvature of a graph convolutional filter function. In reality, we are uncertain about whether we should retain or cut off the frequency at a certain point unless we have expert domain knowledge. In this paper, we propose Automatic Graph Convolutional Networks (AutoGCN) to capture the full spectrum of graph signals and automatically update the bandwidth of graph convolutional filters. While it is based on graph spectral theory, our AutoGCN is also localized in space and has a spatial form. Experimental results show that AutoGCN achieves significant improvement over baseline methods which only work as low-pass filters.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.