Disentangled Generative Graph Representation Learning

TL;DR

This paper introduces DiGGR, a self-supervised framework for learning disentangled graph representations, improving robustness and explainability by guiding mask modeling with latent factors, and demonstrating superior performance on multiple datasets.

Contribution

The paper proposes a novel disentangled generative graph learning method that enhances representation interpretability and robustness, addressing key challenges in existing GRL approaches.

Findings

DiGGR outperforms previous self-supervised methods on 11 datasets.

Disentanglement improves robustness and explainability of graph representations.

End-to-end joint learning effectively captures disentangled factors.

Abstract

Recently, generative graph models have shown promising results in learning graph representations through self-supervised methods. However, most existing generative graph representation learning (GRL) approaches rely on random masking across the entire graph, which overlooks the entanglement of learned representations. This oversight results in non-robustness and a lack of explainability. Furthermore, disentangling the learned representations remains a significant challenge and has not been sufficiently explored in GRL research. Based on these insights, this paper introduces DiGGR (Disentangled Generative Graph Representation Learning), a self-supervised learning framework. DiGGR aims to learn latent disentangled factors and utilizes them to guide graph mask modeling, thereby enhancing the disentanglement of learned representations and enabling end-to-end joint learning. Extensive experiments on 11 public datasets for two different graph learning tasks demonstrate that DiGGR consistently outperforms many previous self-supervised methods, verifying the effectiveness of the proposed approach.