Robust Subgraph Learning by Monitoring Early Training Representations

arXiv:2403.09901v1 Announce Type: new
Abstract: Graph neural networks (GNNs) have attracted significant attention for their outstanding performance in graph learning and node classification tasks. However, their vulnerability to adversarial attacks, particularly through susceptible nodes, poses a challenge in decision-making. The need for robust graph summarization is evident in adversarial challenges resulting from the propagation of attacks throughout the entire graph. In this paper, we address both performance and adversarial robustness in graph input by introducing the novel technique SHERD (Subgraph …

abstract adversarial adversarial attacks arxiv attacks attention challenge challenges classification cs.cr cs.lg decision gnns graph graph learning graph neural networks however making monitoring networks neural networks node nodes performance robust summarization tasks through training type vulnerability