解决模型遗忘时误删相关数据的问题，提升遗忘准确性与保留数据性能。
Machine Unlearning under Retain-Forget Entanglement
- 分两阶段优化：先增强遗忘样本损失，再用Wasserstein-2距离正则化保护相关数据
- 在多个数据集和模型上实现更高遗忘精度与保留数据准确率
- 适合需要高可靠遗忘的隐私敏感场景，如医疗或金融建模
在机器遗忘中，遗忘部分数据往往并非孤立任务。当保留样本与被遗忘样本共享预训练特征或具有强语义相似性时，可能被意外影响。为此，我们提出一种新型两阶段优化框架，以应对这种保留-遗忘纠缠问题。第一阶段采用增强拉格朗日方法，在提升遗忘样本损失的同时，保持与遗忘集无关的保留样本准确率；第二阶段引入基于Wasserstein-2距离的梯度投影正则化，缓解语义相关保留样本的性能下降，同时不损害遗忘目标。我们在多个遗忘任务、标准基准数据集及多种神经网络架构上进行了全面实验，结果表明该方法在有效且可靠的遗忘基础上，优于现有基线，在保留准确性与遗忘保真度方面均有提升。
原文摘要 · Abstract (English)
Forgetting a subset in machine unlearning is rarely an isolated task. Often, retained samples that are closely related to the forget set can be unintentionally affected, particularly when they share correlated features from pretraining or exhibit strong semantic similarities. To address this challenge, we propose a novel two-phase optimization framework specifically designed to handle such retai-forget entanglements. In the first phase, an augmented Lagrangian method increases the loss on the forget set while preserving accuracy on less-related retained samples. The second phase applies a gradient projection step, regularized by the Wasserstein-2 distance, to mitigate performance degradation on semantically related retained samples without compromising the unlearning objective. We validate our approach through comprehensive experiments on multiple unlearning tasks, standard benchmark datasets, and diverse neural architectures, demonstrating that it achieves effective and reliable unlearning while outperforming existing baselines in both accuracy retention and removal fidelity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。