过渡中的持续学习
Continual Learning in Transition
浏览论文内容
中文总结 AI 辅助
本文系统综述持续学习从以参数为中心向系统级适配的转变，通过时机、方式、位置三轴框架分析其演化，讨论相关挑战与未来方向。
中文摘要 AI 辅助
经典持续学习（CL）主要聚焦于通过以参数为中心的机制，如训练策略、架构设计和权重适配，使模型能够更新并保留知识。然而，新兴范式正重塑CL的范围，使其超越这种传统的模型适配视角。例如，策略内学习拓宽了更新机制的空间；测试时训练将CL从训练阶段扩展到推理阶段；而外部控制组件，如记忆、技能库和交互协议，将模型能力的演化边界扩展到远超出静态参数空间的范围。总体而言，这些发展表明一种从以参数为中心的学习向系统级适配的转变。为了表征这种转变，我们从三个维度考察持续学习的演化：学习发生的时机（When）、方式（How）和位置（Where）。How维度涵盖策略外、策略内以及超越梯度的优化机制；When维度涵盖预训练、训练后和推理时阶段的演化；Where维度划分内部参数与外部结构约束内发生的更新。基于这一三轴框架，我们系统地综述了代表性方法，追踪了持续学习正在发生的转变，并讨论了这一范式转变带来的关键挑战、更广泛的影响以及未来方向。
英文摘要
Classical continual learning (CL) has primarily focused on enabling models to update and retain knowledge through parameter-centric mechanisms, e.g., training strategies, architectural designs, and weight adaptation. However, emerging paradigms are reshaping the scope of CL beyond this traditional model adaptation view. For instance, on-policy learning broadens the space of update mechanisms; test-time training extends CL from the training phase to inference; and external harness components such as memory, skill libraries, and interaction protocols extend the evolutionary boundaries of model capabilities far beyond the static parameter space. Collectively, these developments indicate a transition from parameter-centric learning toward system-level adaptation. To characterize this transition, we examine the evolution of continual learning through three dimensions: When, How, and Where learning occurs. The How dimension encompasses off-policy, on-policy, and beyond-gradient optimization mechanics. The When dimension captures evolution across pre-training, post-training, and inference-time stages. The Where dimension delineates updates occurring within internal parameters versus external structural constraints. Anchored by this tri-axial framework, we systematically survey representative methods, trace the ongoing transition of continual learning, and discuss the key challenges, broader implications, and future directions arising from this paradigm shift.
发表机构
- Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
- National University of Singapore（新加坡国立大学）
机构由 AI 辅助整理，请以论文原文为准。
