这篇论文用实验告诉你：模块化在持续学习中不是万能的，维度低时才有用，帮你判断何时该用模块化设计。
该研究在A-B-A范式下比较了任务划分循环网络与单网络基线在持续学习中的表现。高维“lazy”状态中，两种架构性能相近，模块化收益小。低维“rich”状态中，模块化网络形成梯度任务特异子空间，对相似任务重叠、中等相似对齐、不相似分离，实现更组合化的组织。结果表明，初始化尺度诱导的表征维度是决定模块化结构是否有利于持续学习的关键因素。
Dimensionality Controls When Modularity Helps in Continual Learning
Compositional learning systems must balance plasticity, the ability to acquire new knowledge, with stability, the preservation of previously learned components, especially when tasks share structure and risk interference. We study how modular architecture, task similarity, and representational dimensionality jointly shape compositional continual learning in a sequential A-B-A paradigm, comparing a task-partitioned recurrent network to a single-network baseline while inducing high- and low-dimensional regimes via weight-scale manipulations. In a high-dimensional "lazy" regime, both architectures achieve similar performance and internal geometry, suggesting that explicit modular structure has little impact when representations are weakly constrained. In a lower-dimensional "rich" regime, modularity becomes decisive: the modular network develops graded task-specific subspaces that overlap for similar tasks, partially align for moderately dissimilar tasks, and separate for dissimilar tasks, yielding a more compositional and interpretable organization than the single network. These findings identify the representational regime induced by initialization scale, which co-varies with representational dimensionality, as a key factor governing when compositional, modular structure is functionally beneficial in continual learning, and support viewing safety and robustness as problems of adaptive allocation of representational subspaces rather than fixed separation versus sharing.