提出新方法，高效删除模型中特定数据影响，精度更高。
Improved Localized Machine Unlearning Through the Lens of Memorization
- 基于记忆特性定位关键参数，精准缩小修改范围。
- 新算法DEL在多个数据集上刷新未学习性能纪录。
- 适合需快速更新模型、保护隐私的场景使用。
机器遗忘指在模型训练完成后，高效移除特定训练数据的影响，对提升模型准确性（如清除过时、错误标注或恶意数据）至关重要。本文研究局部化遗忘，即仅针对识别出的小规模参数子集进行操作。受记忆化研究启发，提出一种改进的参数定位策略，与现有遗忘算法结合后表现优异。进一步提出新算法Deletion by Example Localization (DEL)，根据该定位策略重置被认为最关键的参数，并进行微调。在多个数据集、遗忘集合和评估指标上的大量实验表明，DEL在未学习指标上达到新SOTA，优于局部与全参数方法，且仅修改少量参数；同时在测试准确率上也超越当前最优局部遗忘方法。
原文摘要 · Abstract (English)
Machine unlearning refers to removing the influence of a specified subset of training data from a machine learning model, efficiently, after it has already been trained. This is important for key applications, including making the model more accurate by removing outdated, mislabeled, or poisoned data. In this work, we study localized unlearning, where the unlearning algorithm operates on a (small) identified subset of parameters. Drawing inspiration from the memorization literature, we propose an improved localization strategy that yields strong results when paired with existing unlearning algorithms. We also propose a new unlearning algorithm, Deletion by Example Localization (DEL), that resets the parameters deemed-to-be most critical according to our localization strategy, and then finetunes them. Our extensive experiments on different datasets, forget sets and metrics reveal that DEL sets a new state-of-the-art for unlearning metrics, against both localized and full-parameter methods, while modifying a small subset of parameters, and outperforms the state-of-the-art localized unlearning in terms of test accuracy too.
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。