A Causality-Aligned Structure Rationalization Scheme Against Adversarial Biased Perturbations for Graph Neural Networks

• Main Authors: JIA, Ju, MA, Siqi, LIU, Yang, WANG, Lina, DENG, Robert H.
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Perturbation methods; Predictive models; Reliability; Robustness; Graph neural networks; Data models; Correlation; Adversarial biased perturbations; spurious correlations; invariant causal rationales; OOD generalization; Information Security
• Online Access: https://ink.library.smu.edu.sg/sis_research/8501
• Institution: Singapore Management University

The graph neural networks (GNNs) are susceptible to adversarial perturbations and distribution biases, which pose potential security concerns for real-world applications. Current endeavors mainly focus on graph matching, while the subtle relationships between the nodes and structures of graph-struct...