Adaptive Continual Learning: Rapid Adaptation and Knowledge Refinement

Jin Du, Yuhong Yang, Jie Ding

Primary Area: transfer learning, meta learning, and lifelong learning

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.

Keywords: Continual learning, Learning theory

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We consider a novel lifelong learning scenario highlighting continual knowledge refinement and utilization, where tasks are possibly recurring without known boundaries. We propose an algorithm with theoretical analysis and a scalable implementation.

Abstract: Continual learning (CL) is an emerging research area aiming to emulate human learning throughout a lifetime. Most existing CL approaches primarily focus on mitigating catastrophic forgetting, a phenomenon where performance on old tasks declines while learning new ones. However, human learning involves not only retaining knowledge but also quickly recognizing the current environment, recalling related knowledge, and refining it for improved performance. In this work, we introduce a new problem setting, Adaptive CL, which captures these aspects in an online, possibly recurring task environment without explicit task boundaries or identities. We propose the LEARN algorithm to efficiently explore, recall, and refine knowledge in such environments. We provide theoretical guarantees from two perspectives: online prediction with tight regret bounds and asymptotic consistency of knowledge. Additionally, we present a scalable implementation that requires only first-order gradients for training deep learning models. Our experiments demonstrate that the LEARN algorithm is highly effective in exploring, recalling, and refining knowledge in adaptive CL environments, resulting in superior performance compared to competing methods.

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.

Submission Number: 6669