Repository logo
 

Towards Causal Replay for Knowledge Rehearsal in Continual Learning

Accepted version
Peer-reviewed

Loading...
Thumbnail Image

Type

Conference Object

Change log

Authors

Cheong, J 
Kalkan, S 
Gunes, H 

Abstract

Given the challenges associated with the real-world deployment of Machine Learning (ML) models, especially towards efficiently integrating novel information on the go, both Continual Learning (CL) and Causality have been proposed and investigated individually as potent solutions. Despite their complementary nature, the bridge between them is still largely unexplored. In this work, we focus on causality to improve the learning and knowledge preservation capabilities of CL models. In particular, positing Causal Replay for knowledge rehearsal, we discuss how CL-based models can benefit from causal interventions towards improving their ability to replay past knowledge in order to mitigate forgetting.

Description

Keywords

Causality, Continual Learning, Pseudo-rehearsal, Rehearsal

Journal Title

Proceedings of Machine Learning Research

Conference Name

Continual Causality Bridge Program at the AAAI Conference on Artificial Intelligence 2023

Journal ISSN

2640-3498

Volume Title

Publisher

PMLR

Publisher DOI

Sponsorship
Engineering and Physical Sciences Research Council (EP/R030782/1)
Alan Turing Institute (ATIPO000004438)
EPSRC, Alan Turing Institute, Cambridge Commonwealth Trust