MIT团队发现机器持续遗忘中的可塑性崩溃现象，解释了为什么模型会逐渐丧失遗忘能力，甚至重新记住已删除信息。
研究人员发现深度神经网络在持续机器学习中存在可塑性崩溃问题。该研究通过理论分析表明，持续遗忘操作会在参数空间中累积几何约束，导致饱和子空间限制未来更新。实验在多种架构、数据集和方法上验证了这一现象，表现为两种失效模式：前向失效和后向失效。这一发现揭示了机器遗忘系统长期可靠性的关键障碍。
On the Plasticity Collapse in Continual Machine Unlearning
Machine unlearning enables deep neural networks to selectively remove the influence of specific data in response to privacy and regulatory requirements. While prior work largely studies single-shot unlearning, real-world systems must accommodate continual unlearning, where multiple unlearning requests occur sequentially over time. In this work, we identify a fundamental limitation of this setting: plasticity collapse, a progressive breakdown in a model's ability to effectively forget. Through theoretical analysis of continual unlearning dynamics, we show that continual unlearning operations accumulate geometric constraints in parameter space, leading to saturated subspaces that restrict future updates. This structural effect induces two distinct failure modes: (1) Forward failure -- diminishing forgetting quality for subsequent tasks, and (2) Backward failure -- spontaneous re-memorization of previously forgotten information. Extensive experiments across multiple architectures, datasets, and methods in image classification confirm that plasticity collapse is not an artifact of specific implementations, but a pervasive phenomenon inherent to continual unlearning. Our findings reveal a critical barrier to the long-term reliability of machine unlearning systems and motivate the development of plasticity-preserving unlearning algorithms. Our code is available at https://github.com/TIML-Group/Continual-Machine-Unlearning-Plasticity-Collapse