Dimensionwise Separable 2-D Graph Convolution for Unsupervised and Semi-Supervised Learning on Graphs

TL;DR

This paper introduces a novel 2-D graph convolution method that jointly models object links and attribute relations, improving node representation learning for classification and clustering tasks on real-world networks.

Contribution

It proposes a computationally efficient dimensionwise separable 2-D graph convolution (DSGC) that captures attribute relations, enhancing the modeling capability over traditional 1-D GCNs.

Findings

DSGC reduces intra-class variance in node features.

Modeling attribute relations improves performance on node classification.

DSGC outperforms state-of-the-art methods on real-world networks.

Abstract

Graph convolutional neural networks (GCN) have been the model of choice for graph representation learning, which is mainly due to the effective design of graph convolution that computes the representation of a node by aggregating those of its neighbors. However, existing GCN variants commonly use 1-D graph convolution that solely operates on the object link graph without exploring informative relational information among object attributes. This significantly limits their modeling capability and may lead to inferior performance on noisy and sparse real-world networks. In this paper, we explore 2-D graph convolution to jointly model object links and attribute relations for graph representation learning. Specifically, we propose a computationally efficient dimensionwise separable 2-D graph convolution (DSGC) for filtering node features. Theoretically, we show that DSGC can reduce intra-class variance of node features on both the object dimension and the attribute dimension to learn more effective representations. Empirically, we demonstrate that by modeling attribute relations, DSGC achieves significant performance gain over state-of-the-art methods for node classification and clustering on a variety of real-world networks. The source code for reproducing the experimental results is available at https://github.com/liqimai/DSGC.