发表机构
University of Manchester; University of Sheffield; Paris Dauphine - PSL University（曼彻斯特大学; 谢菲尔德大学; 巴黎多芬大学 - 巴黎文理研究大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有机器遗忘方法易对相似保留样本造成附带损害的问题，提出感知保留集的定位方法，结合余弦相似度构建评估集，在CIFAR-10与ResNet18的11组实验中验证了方法的有效性。
AI 中文摘要
机器遗忘用于从已训练模型中移除用户指定训练样本的影响，无需从头重新训练。基于定位的方法通过识别有影响力的模型参数子集提升遗忘效率，但现有方法仅基于遗忘集重要性选择参数，忽略了参数在保留数据中的作用，常对语义相似的保留样本造成附带损害。本文提出一种感知保留集的定位方法，同时考虑参数对遗忘数据和保留数据的重要性；还引入保留相似评估集，通过模型嵌入空间中的余弦相似度构建，以直接测量附带损害。在CIFAR-10数据集和ResNet18模型的11种实验设置中，本文方法在持续降低附带损害的同时提升了标准遗忘指标，证明了感知保留集的定位在感知相似度的机器遗忘中的有效性。
英文摘要
Machine unlearning removes the influence of user-specified training examples from a trained model, avoiding the need to retrain it from scratch. Localization-based methods improve unlearning efficiency by identifying a subset of influential model parameters. However, existing approaches select parameters based solely on forget-set importance, neglecting their role in retained dataset and often causing collateral damage to semantically similar retained examples. We address this limitation with a retain-aware localization method that considers parameter importance to both forgotten and retained data. We also introduce a retain-similar evaluation set, constructed using cosine similarity in the model embedding space, to directly measure collateral damage. Across eleven experimental settings on CIFAR-10 dataset and ResNet18 model, our method consistently reduces collateral damage while improving standard unlearning metrics, demonstrating the effectiveness of retain-aware localization for similarity-aware machine unlearning.
