Iterative Relaxing Gradient Projection for Continual Learning

Zeyuan Yang, Zonghan Yang, Peng Li, Yang Liu

Keywords: continual learning, gradient projection methods

Abstract: A critical capability for intelligent systems is to continually learn given a sequence of tasks. An ideal continual learner should be able to avoid catastrophic forgetting and effectively leverage past learned experiences to master new knowledge. Among different continual learning algorithms, gradient projection approaches impose hard constraints on the optimization space for new tasks to minimize task interference, yet hinder forward knowledge transfer at the same time. Recent methods use expansion-based techniques to relax the constraints, but a growing network can be computationally expensive. Therefore, it remains a challenge whether we can improve forward knowledge transfer for gradient projection approaches \textit{using a fixed network architecture}. In this work, we propose the Iterative Relaxing Gradient Projection (IRGP) framework. The basic idea is to iteratively search for the parameter subspaces most related to the current task and relax these parameters, then reuse the frozen spaces to facilitate forward knowledge transfer while consolidating previous knowledge. Our framework requires neither memory buffers nor extra parameters. Extensive experiments have demonstrated the superiority of our framework over several strong baselines. We also provide theoretical guarantees for our iterative relaxing strategies.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning

TL;DR: We propose a novel gradient projection approach to facilitate forward knowledge transfer within a fixed network capacity by iterative searching and relaxing the critical subspace of the frozen space.