Topology Adaptive Graph Convolutional Networks

TL;DR

This paper introduces TAGCN, a novel vertex-domain graph convolutional network that adaptively designs fixed-size filters for graphs, achieving better performance and computational efficiency without approximation.

Contribution

The paper presents a systematic design of adaptive, fixed-size filters for graph convolution in the vertex domain, avoiding spectral approximation.

Findings

TAGCN outperforms spectral CNNs on multiple datasets.

It is computationally simpler than recent methods.

TAGCN maintains properties of traditional CNNs for grid data.

Abstract

Spectral graph convolutional neural networks (CNNs) require approximation to the convolution to alleviate the computational complexity, resulting in performance loss. This paper proposes the topology adaptive graph convolutional network (TAGCN), a novel graph convolutional network defined in the vertex domain. We provide a systematic way to design a set of fixed-size learnable filters to perform convolutions on graphs. The topologies of these filters are adaptive to the topology of the graph when they scan the graph to perform convolution. The TAGCN not only inherits the properties of convolutions in CNN for grid-structured data, but it is also consistent with convolution as defined in graph signal processing. Since no approximation to the convolution is needed, TAGCN exhibits better performance than existing spectral CNNs on a number of data sets and is also computationally simpler than other recent methods.