菜单

关于 🐙 GitHub
arXiv 提交日期: 2026-06-29
📄 Abstract - The Forgetting-Retention Dilemma: Certified Unlearning Theory in Continual Learning

Machine unlearning aims to eliminate the influence of specific data from trained models to safeguard privacy. However, this presents a significant challenge in the context of continual learning (CL), where models update sequentially on dynamic datasets. A major limitation is that current certified unlearning algorithms fail to account for the complex, cumulative model evolution inherent to CL framework. In this work, we establish the first theoretical foundation bridging CL and machine unlearning. We formulate the CL's unlearning objective as the minimization of post-unlearning excess risk, which decomposes into CL excess risk and unlearning loss, characterizing the fundamental trade-off between preserving historical knowledge and targeted forgetting. Under mild assumptions, we first establish an upper bound for the CL excess risk in non-convex models. We then adapt two certified unlearning approaches, gradient-based and Hessian-based, to the CL framework. Our analysis reveals that while the gradient-based approach is less effective than the Hessian-based method in minimizing unlearning loss, it offers the distinct advantage of nearly zero storage overhead for enabling unlearning. This insight motivates a hybrid strategy that reduces storage costs while maintaining post-unlearning performance. Experimental results further validate our theoretical findings.

顶级标签: machine learning theory
详细标签: certified unlearning continual learning forgetting-retention dilemma gradient-based unlearning hessian-based unlearning 或 搜索:

持续学习中的认证遗忘:遗忘-保留困境的解决 / The Forgetting-Retention Dilemma: Certified Unlearning Theory in Continual Learning


1️⃣ 一句话总结

本文首次建立了持续学习中认证遗忘的理论基础,提出了遗忘-保留困境的概念,并设计了基于梯度和基于Hessian的两种遗忘算法及其混合策略,在理论保证和实际存储成本之间取得了平衡。


2️⃣ 论文创新点

1. 遗忘-保留困境的发现与形式化

2. 实践驱动的遗忘-性能平衡理论

3. 两种互补的认证遗忘算法

4. 同步与异步遗忘请求的区分与分析


3️⃣ 主要结果与价值

结果亮点

实际价值


4️⃣ 术语表

源自 arXiv: 2606.29832