Factorizable Graph Convolutional Networks

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.

Accepted by NeurIPS 2020

References in corpus (6)

• Benchmarking Graph Neural Networks
• Learning Disentangled Representations with Semi-Supervised Deep Generative Models
• Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations
• Learning Disentangled Representations for Recommendation
• Distilling Knowledge from Graph Convolutional Networks
• Independence Promoted Graph Disentangled Networks

Cited by in corpus (8)

• Model Degradation Hinders Deep Graph Neural Networks
• Contrastive Model Inversion for Data-Free Knowledge Distillation
• Exploring Edge Disentanglement for Node Classification
• Predicting the Silent Majority on Graphs: Knowledge Transferable Graph Neural Network
• GraphMixup: Improving Class-Imbalanced Node Classification on Graphs by Self-supervised Context Prediction
• Multi-source Unsupervised Domain Adaptation on Graphs with Transferability Modeling
• Adversarial Graph Disentanglement
• Predicting Scientific Impact Through Diffusion, Conformity, and Contribution Disentanglement