There has been a growing interest in Machine Unlearning recently, primarily due to legal requirements such as the General Data Protection Regulation (GDPR) and the California Consumer Privacy Act. Thus, multiple approaches were presented to remove the influence of specific target data points from a trained model. However, when evaluating the success of unlearning, current approaches either use adversarial attacks or compare their results to the optimal solution, which usually incorporates retraining from scratch. We argue that both ways are insufficient in practice. In this work, we present an evaluation metric for Machine Unlearning algorithms based on epistemic uncertainty. This is the first definition of a general evaluation metric for Machine Unlearning to our best knowledge.
翻译:最近,人们日益关注机器脱盲问题,这主要是由于《一般数据保护条例》和《加利福尼亚州消费者隐私法》等法律要求,因此,提出了多种办法消除特定目标数据点从经过培训的模式中的影响,但是,在评价脱学成功与否时,目前的办法要么使用对抗性攻击,要么将其结果与最佳解决办法(通常包括从零开始的再培训)进行比较。我们争辩说,这两种办法在实践中都不够充分。在这项工作中,我们提出了基于认知不确定性的机器脱学算法的评价标准。这是根据我们的最佳知识进行机器脱盲学习的一般评价标准的第一个定义。