Machine unlearning (MU) is to forget data from a well-trained model, which is practically important due to the ``right to be forgotten''. The unlearned model should approach the retrained model, where the forgetting data are not involved in the training process and hence do not contribute to the retrained model. Considering the forgetting data's absence during retraining, we think unlearning should withdraw their contribution from the pre-trained model. The challenge is that when tracing the learning process is impractical, how to quantify and detach sample's contribution to the dynamic learning process using only the pre-trained model. We first theoretically discover that sample's contribution during the process will reflect in the learned model's sensitivity to it. We then practically design a novel method, namely MU-Mis (Machine Unlearning by Minimizing input sensitivity), to suppress the contribution of the forgetting data. Experimental results demonstrate that MU-Mis can unlearn effectively and efficiently without utilizing the remaining data. It is the first time that a remaining-data-free method can outperform state-of-the-art (SoTA) unlearning methods that utilize the remaining data.

翻译：机器遗忘（MU）旨在使训练良好的模型遗忘特定数据，这在实践中具有重要意义，因为它关系到“被遗忘权”。遗忘后的模型应接近重新训练的模型，其中遗忘数据不参与训练过程，因此对重新训练模型没有贡献。考虑到重新训练过程中遗忘数据的缺失，我们认为遗忘应当从预训练模型中撤回这些数据的贡献。挑战在于，当追溯学习过程不可行时，如何仅使用预训练模型来量化并剥离样本对动态学习过程的贡献。我们首先从理论上发现，样本在学习过程中的贡献会反映在已训练模型对其的敏感性上。随后，我们实际设计了一种新方法，即MU-Mis（通过最小化输入敏感性的机器遗忘），来抑制遗忘数据的贡献。实验结果表明，MU-Mis能够在不利用剩余数据的情况下，有效且高效地实现遗忘。这是首次有无需剩余数据的方法在性能上超越了利用剩余数据的最先进（SoTA）遗忘方法。