Make Continual Learning Stronger via C-Flat

arXiv:2404.00986v1 Announce Type: new
Abstract: Model generalization ability upon incrementally acquiring dynamically updating knowledge from sequentially arriving tasks is crucial to tackle the sensitivity-stability dilemma in Continual Learning (CL). Weight loss landscape sharpness minimization seeking for flat minima lying in neighborhoods with uniform low loss or smooth gradient is proven to be a strong training regime improving model generalization compared with loss minimization based optimizer like SGD. Yet only a few works have discussed this training regime for CL, proving …

abstract arxiv continual cs.cv cs.lg gradient knowledge landscape loss low model generalization sensitivity stability tasks type uniform via