通过细粒度超梯度实现从离线到在线的无记忆且无任务持续学习
From Offline to Online Memory-Free and Task-Free Continual Learning via Fine-Grained Hypergradients
AI总结：
针对在线持续学习中无任务、无记忆方法难以适配的问题，本文用轻量级原型结合细粒度超梯度重加权缓解梯度不平衡，显著提升性能并超过在线基线。
摘要：
持续学习（CL）旨在从底层分布随时间变化的非平稳数据流中学习。尽管近期进展已在离线CL（offCL）设定下产生了高效的无记忆方法——该设定中任务预先已知且数据可被重新访问——但在线CL（onCL）仍由基于记忆的方法主导。从offCL到onCL的转换颇具挑战，因为许多离线方法依赖于：（1）任务边界的先验知识；（2）复杂的调度或优化方案；当数据顺序到达且只能被查看一次时，这两者都不可用。本文研究如何将最先进的无记忆offCL方法适配到在线设定。我们首先表明，用轻量级原型增强这些方法可显著提升性能，但代价是梯度不平衡加剧，导致学习偏向较早的任务。为解决该问题，我们提出Fine-Grained Hypergradients（细粒度超梯度），这是一种用于在训练期间重新平衡梯度更新的在线机制。实验表明，原型记忆与超梯度重加权之间的协同作用大幅提升了无记忆方法在onCL中的性能，并超过了onCL基线。代码将在论文被接收后发布。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
