被遗忘还是公平：揭示机器遗忘方法的公平性影响
To Be Forgotten or To Be Fair: Unveiling Fairness Implications of Machine Unlearning Methods
AI总结：
本文首次研究机器遗忘方法的公平性影响，通过在三种删除策略下对比 SISA、AmnesiacML 和 ORTR，发现非均匀删除时 SISA 公平性更优，为软件工程师权衡被遗忘权与公平性提供依据。
摘要：
被遗忘权（RTBF）源于人们不希望因过去的行为而永久处于不利地位的愿望。为此，数据删除需要是深度且永久的，并且应从机器学习模型中移除。研究人员提出了机器遗忘算法，旨在更高效地从已训练模型中擦除特定数据。然而，这些方法改变了数据输入模型的方式以及训练的执行方式，这可能随后从公平性角度损害人工智能伦理。为了帮助软件工程师在采用这些遗忘方法时做出负责任的决策，我们提出了首个关于机器遗忘方法的研究，以揭示其公平性影响。我们设计并进行了实验，使用三种公平性数据集，在三种不同的删除策略下，对两种典型的机器遗忘方法（SISA 和 AmnesiacML）以及作为基线的重训练方法（ORTR）进行实验。实验结果表明，在非均匀数据删除下，与 ORTR 和 AmnesiacML 相比，SISA 带来更好的公平性，而初始训练和均匀数据删除并不一定会影响所有三种方法的公平性。这些发现揭示了软件工程中的一个重要研究问题，并可以帮助从业者在考虑 RTBF 解决方案时更好地理解公平性方面的潜在权衡。
英文摘要：
The right to be forgotten (RTBF) is motivated by the desire of people not to be perpetually disadvantaged by their past deeds. For this, data deletion needs to be deep and permanent, and should be removed from machine learning models. Researchers have proposed machine unlearning algorithms which aim to erase specific data from trained models more efficiently. However, these methods modify how data is fed into the model and how training is done, which may subsequently compromise AI ethics from the fairness perspective. To help software engineers make responsible decisions when adopting these unlearning methods, we present the first study on machine unlearning methods to reveal their fairness implications. We designed and conducted experiments on two typical machine unlearning methods (SISA and AmnesiacML) along with a retraining method (ORTR) as baseline using three fairness datasets under three different deletion strategies. Experimental results show that under non-uniform data deletion, SISA leads to better fairness compared with ORTR and AmnesiacML, while initial training and uniform data deletion do not necessarily affect the fairness of all three methods. These findings have exposed an important research problem in software engineering, and can help practitioners better understand the potential trade-offs on fairness when considering solutions for RTBF.
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。
