Bayesian Graph Contrastive Learning

TL;DR

This paper introduces a Bayesian approach to graph contrastive learning that models node representations as distributions, enabling uncertainty quantification and improved performance in graph analytics tasks.

Contribution

It presents a novel Bayesian framework for graph contrastive learning that captures uncertainty and enhances model expressiveness over existing deterministic methods.

Findings

Improved accuracy on benchmark datasets

Provides uncertainty estimates for node representations

Eliminates need for hyperparameter search in perturbation probability

Abstract

Contrastive learning has become a key component of self-supervised learning approaches for graph-structured data. Despite their success, existing graph contrastive learning methods are incapable of uncertainty quantification for node representations or their downstream tasks, limiting their application in high-stakes domains. In this paper, we propose a novel Bayesian perspective of graph contrastive learning methods showing random augmentations leads to stochastic encoders. As a result, our proposed method represents each node by a distribution in the latent space in contrast to existing techniques which embed each node to a deterministic vector. By learning distributional representations, we provide uncertainty estimates in downstream graph analytics tasks and increase the expressive power of the predictive model. In addition, we propose a Bayesian framework to infer the probability of perturbations in each view of the contrastive model, eliminating the need for a computationally expensive search for hyperparameter tuning. We empirically show a considerable improvement in performance compared to existing state-of-the-art methods on several benchmark datasets.