arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.05025cs.LG
收藏

减少在线持续学习中表征突变的新见解

New Insights on Reducing Abrupt Representation Change in Online Continual Learning

McGill University(麦吉尔大学);Mila(米拉研究所);Facebook AI Research(脸书人工智能研究院);Toyota Motor Europe(丰田汽车欧洲公司);Concordia University(康考迪亚大学);KU Leuven(鲁汶大学)

Lucas Caccia, Rahaf Aljundi, Nader Asadi, Tinne Tuytelaars, Joelle Pineau, Eugene Belilovsky

摘要:

在在线持续学习范例中,代理必须从不断变化的分布中学习,同时尊重内存和计算约束。经验重放(ER),其中一小部分过去的数据被存储并与新数据一起重放,已经成为一种简单而有效的学习策略。在这项工作中,我们专注于所观察到的数据表示的变化时,出现以前未观察到的类出现在传入的数据流中,新的类必须从以前的区别。我们揭示了新的光在这个问题上显示,应用ER导致新添加的类的表示与以前的类显着重叠,导致高度破坏性的参数更新。基于这种实证分析,我们提出了一种新的方法,通过屏蔽学习到的表示来适应新的类来缓解这个问题。我们表明,使用不对称的更新规则推动新的类,以适应旧的(而不是相反),这是更有效的,特别是在任务边界,其中大部分的遗忘通常发生。实证结果表明,在标准持续学习基准上,强基线有显著的收益。

英文摘要:

In the online continual learning paradigm, agents must learn from a changing distribution while respecting memory and compute constraints. Experience Replay (ER), where a small subset of past data is stored and replayed alongside new data, has emerged as a simple and effective learning strategy. In this work, we focus on the change in representations of observed data that arises when previously unobserved classes appear in the incoming data stream, and new classes must be distinguished from previous ones. We shed new light on this question by showing that applying ER causes the newly added classes' representations to overlap significantly with the previous classes, leading to highly disruptive parameter updates. Based on this empirical analysis, we propose a new method which mitigates this issue by shielding the learned representations from drastic adaptation to accommodate new classes. We show that using an asymmetric update rule pushes new classes to adapt to the older ones (rather than the reverse), which is more effective especially at task boundaries, where much of the forgetting typically occurs. Empirical results show significant gains over strong baselines on standard continual learning benchmarks.

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。

↑