Pairwise Gaussian Graph Convolutional Networks: Defense Against Graph Adversarial Attack

Abstract

As a research hotspot for graph mining technology, Graph Convolutional Networks (GCN) have achieved remarkable performance in the fields of wireless networks, Internet of Things, and edge computing. However, recent studies have shown that GCN is vulnerable to adversarial attack; that is, even imperceptible intentional perturbations on graph structure or node attributes can significantly change classification results. This paper proposes a novel graph convolutional network, Pairwise Gaussian Graph Convolutional Networks (PGGCN), in which a pairwise architecture is designed for GCN model construction and training. This elegant design enables PGGCN to mitigate the effects of adversarial attack and thus improve model robustness while guaranteeing classification accuracy. The performance of PGGCN is validated through extensive experimental results, which confirm that PGGCN can effectively improve the robustness of GCN while ensuring classification accuracy.