迈向高效的无数据机器遗忘
Toward Efficient Data-Free Unlearning
AI总结：
针对无数据机器遗忘中过度过滤导致保留知识蒸馏效率低的问题，提出 Inhibited Synthetic PostFilter (ISPF) 方法，通过减少合成遗忘信息并充分利用合成保留信息，有效提升了遗忘性能并超越现有方法。
摘要：
在无法访问真实数据分布的情况下进行机器遗忘是一项具有挑战性的任务。现有的基于无数据蒸馏的方法通过过滤掉包含遗忘信息的合成样本来实现遗忘，但难以高效地蒸馏与保留相关的知识。在本研究中，我们分析认为该问题是由过度过滤引起的，这减少了合成数据中与保留相关的信息。我们提出了一种新方法 Inhibited Synthetic PostFilter (ISPF)，从两个角度应对这一挑战：首先，Inhibited Synthetic 通过减少合成的遗忘信息；其次，PostFilter 通过充分利用合成样本中与保留相关的信息。实验结果表明，所提出的 ISPF 有效解决了该挑战，并优于现有方法。
英文摘要：
Machine unlearning without access to real data distribution is challenging. The existing method based on data-free distillation achieved unlearning by filtering out synthetic samples containing forgetting information but struggled to distill the retaining-related knowledge efficiently. In this work, we analyze that such a problem is due to over-filtering, which reduces the synthesized retaining-related information. We propose a novel method, Inhibited Synthetic PostFilter (ISPF), to tackle this challenge from two perspectives: First, the Inhibited Synthetic, by reducing the synthesized forgetting information; Second, the PostFilter, by fully utilizing the retaining-related information in synthesized samples. Experimental results demonstrate that the proposed ISPF effectively tackles the challenge and outperforms existing methods.
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。
