Uncertainty in Graph Contrastive Learning with Bayesian Neural Networks

Alexander Möllers, Alexander Immer, Elvin Isufi, Vincent Fortuin

Keywords: Bayesian contrastive learning, Bayesian self-supervised learning, probabilistic contrastive learning

Abstract: Graph contrastive learning has shown great promise when labeled data is scarce, but large unlabeled datasets are available. However, it often does not take uncertainty estimation into account. We show that a variational Bayesian neural network approach can be used to improve not only the uncertainty estimates but also the downstream performance on semi-supervised node-classification tasks. Moreover, we propose a new measure of uncertainty for contrastive learning, that is based on the disagreement in likelihood due to different positive samples.

TL;DR: We improve contrastive learning performance on graphs by using a Bayesian model and develop a new related uncertainty measure.