Xuantao Yang

Can Edge Addition Be Safe and Effective? Adjacency-Centered Augmentation via Langevin and SDE Diffusion for Self-Supervised Graph Anomaly Detection

Edge addition is commonly considered risky in Graph Anomaly Detection (GAD), as random edge addition may induce anomaly–normal connectivity. Consequently, most existing augmentation strategies focus on feature perturbation, edge removal, or subgraph sampling, leaving edge addition largely unexplored