Bayesian Robust Graph Contrastive Learning
Abstract: Graph Neural Networks (GNNs) have been widely used to learn node representations and with outstanding performance on various tasks such as node classification. However, noise, which inevitably exists in real-world graph data, would considerably degrade the performance of GNNs revealed by recent studies. In this work, we propose a novel and robust method, Bayesian Robust Graph Contrastive Learning (BRGCL), which trains a GNN encoder to learn robust node representations. The BRGCL encoder is a completely unsupervised encoder. Two steps are iteratively executed at each epoch of training the BRGCL encoder: (1) estimating the confident nodes and computing the robust cluster prototypes of the node representations through a novel Bayesian nonparametric method; (2) prototypical contrastive learning between the node representations and the robust cluster prototypes. Experiments on public benchmarks demonstrate the superior performance of BRGCL and the robustness of the learned node representations. The code of BRGCL is available at \url{https://anonymous.4open.science/r/BRGCL-code-2FD9/}.
Submission Length: Regular submission (no more than 12 pages of main content)
Assigned Action Editor: ~Ran_He1
Submission Number: 2461
Loading