CUNO: Curriculum and Preference Optimization for Stable Graph Unlearning under Mass Deletion
CUNO is proposed, a curriculum-based graph unlearning framework that removes the forget set progressively, ordering samples by their estimated unlearning difficulty across multiple stages, and employs a distribution-level negative preference optimization objective at each curriculum stage that steers the model away fro...
Chen-Han Zhang, Ali Braytee, M. Bandara et al.
· 0 citations