From Offline to Online Memory-Free and Task-Free Continual Learning via Fine-Grained Hypergradients

TMLR Paper7490 Authors

Abstract: Continual Learning (CL) aims to learn from a non-stationary data stream where the underlying distribution changes over time. While recent advances have produced efficient memory-free methods in the offline CL (offCL) setting, online CL (onCL) remains dominated by memory-based approaches. The transition from offCL to onCL is challenging, as many offline methods rely on (1) prior knowledge of task boundaries and (2) sophisticated scheduling or optimization schemes, both of which are unavailable when data arrives sequentially and can be seen only once. In this paper, we investigate the adaptation of state-of-the-art memory-free offCL methods to the online setting. We first show that augmenting these methods with lightweight prototypes significantly improves performance, albeit at the cost of increased Gradient Imbalance, resulting in a biased learning towards earlier tasks. To address this issue, we formulate Fine-Grained Hypergradients as an online mechanism for rebalancing gradient updates during training. Our experiments demonstrate that the synergy between prototype memory and hypergradient reweighting substantially allows for improved performance of memory-free methods in onCL. Code will be released upon acceptance.

Submission Type: Regular submission (no more than 12 pages of main content)

Assigned Action Editor: ~Mingrui_Liu2

Submission Number: 7490