Cost-Efficient Continual Learning with Sufficient Exemplar Memory

Dong Kyu Cho, Taesup Moon, Rumi Chunara, Kyunghyun Cho, Sungmin Cha

Published: 05 Mar 2025, Last Modified: 05 Mar 2025ICLR 2025 Workshop Weight Space Learning PosterEveryoneRevisionsBibTeXCC BY 4.0
Track: tiny / short paper (up to 4 pages)
Keywords: Continual Learning, Model Merging
TL;DR: We study continual learning in a realistic setting where exemplar memory is abundant, while computation resources are limited.
Submission Number: 18