From Offline to Online Memory-Free and Task-Free Continual Learning via Fine-Grained Hypergradients
This work addresses the problem of online continual learning for AI systems that must learn from streaming data without memory, offering a novel solution to gradient imbalance, though it is incremental as it builds on existing offline methods.
The paper tackles the challenge of adapting memory-free continual learning methods from offline to online settings, where data arrives sequentially without task boundaries, by introducing Fine-Grained Hypergradients to rebalance gradient updates, achieving performance improvements that surpass existing online baselines.
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, where tasks are known in advance and data can be revisited, 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 introduce Fine-Grained Hypergradients, an online mechanism for rebalancing gradient updates during training. Our experiments demonstrate that the synergy between prototype memory and hypergradient reweighting substantially enhances the performance of memory-free methods in onCL and surpasses onCL baselines. Code will be released upon acceptance.