Xu-Dong Wang

GLASS: Graph-Language Alignment with Spherical Scoring for Transferable Graph-Level Anomaly Detection

GLASS is introduced, a framework for graph-level anomaly detection (GLAD) that achieves robust cross-domain transferability through graph-language alignment on the unit hypersphere and Spherical Multi-Modal Scoring (SMS), which instantiates von Mises-Fisher kernel density estimators in both graph and text embedding spa...