Restricted orthogonal gradient projection for continual learning

Restricted orthogonal gradient projection for continual learning

Continual learning aims to avoid catastrophic forgetting and effectively leverage learned experiences to master new knowledge. Existing gradient projection approaches impose hard constraints on the optimization space for new tasks to minimize interference, which simultaneously hinders forward knowle...

Full description

Bibliographic Details
Main Authors: Zeyuan Yang, Zonghan Yang, Yichen Liu, Peng Li, Yang Liu
Format: Article
Language:English
Published: KeAi Communications Co. Ltd. 2023-01-01
Series:AI Open
Subjects:
Continual learning
Gradient projection
Forward knowledge transfer
Online Access:http://www.sciencedirect.com/science/article/pii/S2666651023000128

Internet

http://www.sciencedirect.com/science/article/pii/S2666651023000128

Similar Items