Factorizable Graph Convolutional Networks

TL;DR

This paper introduces FactorGCN, a novel graph convolutional network that disentangles complex, intertwined relations in graphs into separate latent factors, improving feature aggregation and downstream task performance.

Contribution

It proposes a new GCN model that explicitly disentangles heterogeneous relations in graphs into multiple factorized graphs, enhancing interpretability and effectiveness.

Findings

Effective disentangling of relations demonstrated on synthetic and real datasets

Improved downstream task performance with factorized features

Qualitative and quantitative validation of disentanglement quality

Abstract

Graphs have been widely adopted to denote structural connections between entities. The relations are in many cases heterogeneous, but entangled together and denoted merely as a single edge between a pair of nodes. For example, in a social network graph, users in different latent relationships like friends and colleagues, are usually connected via a bare edge that conceals such intrinsic connections. In this paper, we introduce a novel graph convolutional network (GCN), termed as factorizable graph convolutional network(FactorGCN), that explicitly disentangles such intertwined relations encoded in a graph. FactorGCN takes a simple graph as input, and disentangles it into several factorized graphs, each of which represents a latent and disentangled relation among nodes. The features of the nodes are then aggregated separately in each factorized latent space to produce disentangled features, which further leads to better performances for downstream tasks. We evaluate the proposed FactorGCN both qualitatively and quantitatively on the synthetic and real-world datasets, and demonstrate that it yields truly encouraging results in terms of both disentangling and feature aggregation. Code is publicly available at https://github.com/ihollywhy/FactorGCN.PyTorch.