Octave Graph Convolutional Network

Heng Chang, Yu Rong, Somayeh Sojoudi, Junzhou Huang, Wenwu Zhu

TL;DR: Octave convolutional learning for graphs in spectral domain within the framework of Graph Convolutional Networks

Abstract: Many variants of Graph Convolutional Networks (GCNs) for representation learning have been proposed recently and have achieved fruitful results in various domains. Among them, spectral-based GCNs are constructed via convolution theorem upon theoretical foundation from the perspective of Graph Signal Processing (GSP). However, despite most of them implicitly act as low-pass filters that generate smooth representations for each node, there is limited development on the full usage of underlying information from low-frequency. Here, we first introduce the octave convolution on graphs in spectral domain. Accordingly, we present Octave Graph Convolutional Network (OctGCN), a novel architecture that learns representations for different frequency components regarding to weighted filters and graph wavelets bases. We empirically validate the importance of low-frequency components in graph signals on semi-supervised node classification and demonstrate that our model achieves state-of-the-art performance in comparison with both spectral-based and spatial-based baselines.

Keywords: Graph Convolutional Networks, Octave Convolution, Graph Mining