遗忘序列中的机器学习反学习
Machine Unlearning in Forgettability Sequence
AI总结：
本文研究机器学习反学习中不同样本的遗忘难度差异，发现高隐私风险样本更难遗忘，并提出由 Ranking 和 SeqUnlearn 模块组成的通用反学习框架 RSU，以实现更精确的遗忘。
摘要：
机器学习反学习（MU）正在成为实现“被遗忘权”的一种有前景的范式，其中任何选定数据点的训练痕迹都可以被消除，同时在反学习后保持模型对一般测试样本的效用。随着遗忘研究的进展，许多基本的开放问题仍未得到解答：不同样本在被遗忘时是否表现出不同的难度？进一步地，由样本各自难度水平决定的遗忘顺序是否会影响遗忘算法的性能？在本文中，我们识别了影响反学习难度和反学习算法性能的关键因素。我们发现，具有更高隐私风险的样本更有可能需要被反学习，这表明不同样本之间的反学习难度存在差异，这促使需要一种更精确的反学习模式。基于这一见解，我们提出了一个通用的反学习框架，称为 RSU，它由 Ranking 模块和 SeqUnlearn 模块组成。
英文摘要：
Machine unlearning (MU) is becoming a promising paradigm to achieve the "right to be forgotten", where the training trace of any chosen data points could be eliminated, while maintaining the model utility on general testing samples after unlearning. With the advancement of forgetting research, many fundamental open questions remain unanswered: do different samples exhibit varying levels of difficulty in being forgotten? Further, does the sequence in which samples are forgotten, determined by their respective difficulty levels, influence the performance of forgetting algorithms? In this paper, we identify key factor affecting unlearning difficulty and the performance of unlearning algorithms. We find that samples with higher privacy risks are more likely to be unlearning, indicating that the unlearning difficulty varies among different samples which motives a more precise unlearning mode. Built upon this insight, we propose a general unlearning framework, dubbed RSU, which consists of Ranking module and SeqUnlearn module.
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。
