IMEX-Reg: Implicit-Explicit Regularization in the Function Space for Continual Learning

arXiv:2404.18161v1 Announce Type: new
Abstract: Continual learning (CL) remains one of the long-standing challenges for deep neural networks due to catastrophic forgetting of previously acquired knowledge. Although rehearsal-based approaches have been fairly successful in mitigating catastrophic forgetting, they suffer from overfitting on buffered samples and prior information loss, hindering generalization under low-buffer regimes. Inspired by how humans learn using strong inductive biases, we propose IMEX-Reg to improve the generalization performance of experience rehearsal in CL under low buffer regimes. Specifically, …

abstract acquired arxiv catastrophic forgetting challenges continual cs.ai cs.cv cs.lg function information knowledge loss networks neural networks overfitting prior regularization samples space type