Defending Graph Convolutional Networks against Dynamic Graph Perturbations via Bayesian Self-supervision

TL;DR

This paper introduces GraphSS, a Bayesian self-supervision approach that enhances the robustness of Graph Convolutional Networks against dynamic graph perturbations, especially under label scarcity conditions.

Contribution

The paper proposes a novel Bayesian self-supervision model, GraphSS, to improve GCN robustness on dynamic graphs with label scarcity, outperforming existing methods.

Findings

GraphSS effectively detects perturbations in dynamic graphs.

GraphSS recovers node classification accuracy under attacks.

The method generalizes across multiple GCN architectures and datasets.

Abstract

In recent years, plentiful evidence illustrates that Graph Convolutional Networks (GCNs) achieve extraordinary accomplishments on the node classification task. However, GCNs may be vulnerable to adversarial attacks on label-scarce dynamic graphs. Many existing works aim to strengthen the robustness of GCNs; for instance, adversarial training is used to shield GCNs against malicious perturbations. However, these works fail on dynamic graphs for which label scarcity is a pressing issue. To overcome label scarcity, self-training attempts to iteratively assign pseudo-labels to highly confident unlabeled nodes but such attempts may suffer serious degradation under dynamic graph perturbations. In this paper, we generalize noisy supervision as a kind of self-supervised learning method and then propose a novel Bayesian self-supervision model, namely GraphSS, to address the issue. Extensive experiments demonstrate that GraphSS can not only affirmatively alert the perturbations on dynamic graphs but also effectively recover the prediction of a node classifier when the graph is under such perturbations. These two advantages prove to be generalized over three classic GCNs across five public graph datasets.