遗忘、可塑性与共观测：持续学习的第三维度

中文摘要 AI 辅助

高效持续学习仍是深度神经网络的核心挑战。尽管灾难性遗忘和可塑性丧失被广泛视为需克服的主要障碍，但本文表明这两个问题无法完全解释朴素顺序训练与离线联合训练间的性能差距。本文强调数据共观测是影响持续学习性能的独立因素，通过将独立数据访问的约束与稳定性、可塑性解耦，系统研究了联合观测训练数据带来的表征收益。实验在通用数据增量“分块”场景下，监督学习和自监督学习范式中均验证了联合训练与独立训练间的一致性能差异，同时缓解了遗忘并控制了可塑性。研究发现，训练数据的同步观测（共观测）对学习器泛化的益处远不止知识保留，且该效应不依赖特定的持续分布偏移。此外，本文从该视角阐释了主流持续学习机制：蒸馏方法仅作为有效的知识保留机制，而记忆重放的经验成功不止于缓解遗忘，还主动将数据共观测的益处重新引入学习过程。

英文摘要

Efficient continual learning remains a fundamental challenge for deep neural networks. While catastrophic forgetting and loss of plasticity are widely considered the primary obstacles to overcome, we show that these two issues cannot fully explain the performance gap between naive sequential training and offline joint training. In this paper, we highlight data co-observation as a distinct factor influencing continual learning performance. By decoupling the constraints of separate data access from stability and plasticity, we systematically investigate the representational benefits gained by observing training data together. Empirically, we demonstrate a consistent performance difference between joint and separate training across both supervised and self-supervised paradigms in generic data-incremental "chunking" scenarios, whilst mitigating forgetting and controlling for plasticity. Our findings indicate that simultaneous observation of training data (co-observation) yields benefits to the learner's generalization that extend well beyond mere knowledge retention, and that this effect does not require a specific continual distribution shift. Furthermore, we contextualize prominent continual learning mechanisms through this lens: while distillation-based approaches act only as effective knowledge retention mechanisms, our results suggest that the empirical success of memory replay goes beyond the mitigation of forgetting, actively reintroducing the benefits of data co-observation into the learning process.

发表机构

• KU Leuven
• ESAT
• Bernoulli Institute（伯努利研究所）
• University of Groningen（格罗宁根大学）

机构由 AI 辅助整理，请以论文原文为准。