DriftGuard-HCL: Concept-Drift-Aware Continual Heterogeneous Graph Contrastive Learning for Evolving Financial Fraud Detection
Dr DriftGuard-HCL is presented, a continual heterogeneous graph-contrastive framework that combines a scalable typed graph-context encoder, semantic-group contrastive regularization, delayed-label replay, and a relation-support-aware drift gate that supports the value of drift-gated adaptation while not constituting ev...