Continual Learning-Unlearning

This paper proposes a unified gradient-based framework for task-agnostic continual learning-unlearning that models continual learning and machine unlearning within a single KL-divergence-based optimization objective, decomposes gradient updates into interpretable components, and introduces a Hessian-informed remain-preserved manifold and the UG-CLU algorithm to balance knowledge acquisition, targeted unlearning, and stability across benchmarks.

May 21, 2025