遗忘相似样本：机器去学习能否做得更好？
Forgetting Similar Samples: Can Machine Unlearning Do it Better?
AI总结：
本文研究了机器去学习在存在相似样本时的有效性，发现现有方法未能有效消除目标样本影响，并提出改进方案。
摘要：
机器去学习，一种使预训练模型能够去除特定训练样本影响的过程，近年来引起了广泛关注。尽管大量研究集中在开发高效的机器去学习策略上，我们认为这些方法主要旨在去除样本而非去除样本对模型的影响，因此忽略了机器去学习的基本定义。在本文中，我们首先进行一项全面研究，评估现有去学习方案在训练数据集包含许多与目标去学习样本相似的样本时的有效性。具体而言，我们评估：现有的去学习方法是否真正遵循机器去学习的原始定义，并在训练数据集中存在相似样本时有效消除所有目标样本的影响？我们进行了广泛实验，使用四个精心构建的数据集并进行了深入分析，发现大多数现有去学习方法在图像和语言模型上的预期性能与实际性能之间存在显著差距，即使对于从头重新训练的基准方法也是如此。此外，我们还探索了增强当前去学习方法的潜在解决方案。
英文摘要：
Machine unlearning, a process enabling pre-trained models to remove the influence of specific training samples, has attracted significant attention in recent years. Although extensive research has focused on developing efficient machine unlearning strategies, we argue that these methods mainly aim at removing samples rather than removing samples' influence on the model, thus overlooking the fundamental definition of machine unlearning. In this paper, we first conduct a comprehensive study to evaluate the effectiveness of existing unlearning schemes when the training dataset includes many samples similar to those targeted for unlearning. Specifically, we evaluate: Do existing unlearning methods truly adhere to the original definition of machine unlearning and effectively eliminate all influence of target samples when similar samples are present in the training dataset? Our extensive experiments, conducted on four carefully constructed datasets with thorough analysis, reveal a notable gap between the expected and actual performance of most existing unlearning methods for image and language models, even for the retraining-from-scratch baseline. Additionally, we also explore potential solutions to enhance current unlearning approaches.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
