Continual learning (CL) algorithms strive to acquire new knowledge while preserving prior information. However, this stability-plasticity trade-off remains a central challenge. This paper introduces a framework that dissects this trade-off, offering valuable insights into CL algorithms. The Readout-Decomposition of Activation Change (RDAC) framework first addresses the stability-plasticity dilemma and its relation to catastrophic forgetting. It relates learning-induced activation changes in the range of prior readouts to the degree of stability and changes in the null space to the degree of plasticity. In deep non-linear networks tackling split-CIFAR-110 tasks, the framework clarifies the stability-plasticity trade-offs of the popular regularization algorithms Synaptic intelligence (SI), Elastic-weight consolidation (EWC), and learning without Forgetting (LwF), and replay-based algorithms Gradient episodic memory (GEM), and data replay. GEM and data replay preserved stability and plasticity, while SI, EWC, and LwF traded off plasticity for stability. The inability of the regularization algorithms to maintain plasticity was linked to them restricting the change of activations in the null space of the prior readout. Additionally, for one-hidden-layer linear neural networks, we derived a gradient decomposition algorithm to restrict activation change only in the range of the prior readouts, to maintain high stability while not further sacrificing plasticity. Results demonstrate that the algorithm maintained stability without significant plasticity loss. The RDAC framework informs the behavior of existing CL algorithms and paves the way for novel CL approaches. Finally, it sheds light on the connection between learning-induced activation/representation changes and the stability-plasticity dilemma, also offering insights into representational drift in biological systems.

翻译：持续学习算法致力于在保持已有知识的同时获取新知识，但稳定性-可塑性权衡仍是核心难题。本文提出一种解构该权衡的框架，为持续学习算法提供重要见解。激活变化解读分解（RDAC）框架首先探讨稳定性-可塑性困境及其与灾难性遗忘的关联，通过将学习引发的激活变化分解为：先验解读值域内的变化对应稳定性程度，零空间内的变化对应可塑性程度。在处理split-CIFAR-110任务的深度非线性网络中，该框架阐明了主流正则化算法——突触智能（SI）、弹性权重巩固（EWC）与无遗忘学习（LwF）——以及基于回放的算法——梯度情景记忆（GEM）与数据回放——的稳定性-可塑性权衡机制。实验表明GEM与数据回放能同时保持稳定性与可塑性，而SI、EWC与LwF以牺牲可塑性为代价换取稳定性。正则化算法无法维持可塑性的原因在于其限制了先验解读零空间内的激活变化。此外，针对单隐层线性神经网络，我们推导出梯度分解算法，仅限制先验解读值域内的激活变化，从而在保持高稳定性的同时避免进一步损失可塑性。结果表明该算法在维持稳定性的同时未出现显著可塑性下降。RDAC框架既揭示了现有持续学习算法的运行机理，又为新型持续学习方法开辟道路。最后，该框架阐明了学习引发的激活/表征变化与稳定性-可塑性困境的内在关联，并为生物系统中的表征漂移现象提供了理论洞见。