Back to publications
Resilient Graph Neural Networks: A Coupled Dynamical Systems Approach
Paper Details
Published: 2024/09/11
DOI: 10.48550/arXiv.2311.06942
ARXIV ID: 2311.06942v3
Paper Links
PDFGraph Neural Networks (GNNs) have established themselves as a key component in addressing diverse graph-based tasks. Despite their notable successes, GNNs remain susceptible to input perturbations in the form of adversarial attacks. This paper introduces an innovative approach to fortify GNNs against adversarial perturbations through the lens of coupled dynamical systems. A distinctive feature of the proposed approach is the simultaneous learned evolution of both the node features and the adjacency matrix, yielding an intrinsic enhancement of model robustness to perturbations in the input features and the connectivity of the graph.
Authors
D. Murarib
F. Sherrya