提出新方法让模型忘记数据，同时保持识别能力不下降。
Distribution-Level Feature Distancing for Machine Unlearning: Towards a Better Trade-off Between Model Utility and Forgetting
- 通过调整特征分布，让被遗忘样本的特征远离原分布。
- 单轮训练即可有效遗忘，且在人脸数据集上表现更优。
- 适合需要删除用户数据但仍要保持模型精度的场景。
随着深度学习应用爆发式增长和隐私关切加剧，‘被遗忘的权利’已成为多个AI领域的重要需求。例如，在人脸识别系统中，某些个体可能希望移除其个人数据。然而，深度神经网络有时会意外泄露身份信息，导致删除困难。尽管现有机器遗忘算法旨在使模型遗忘特定数据，我们发现遗忘过程会引发意外的性能下降——特征与真实标签间的相关性减弱，即相关性坍塌。为此，我们提出分布级特征分离（DLFD），一种新方法，在高效遗忘的同时保留任务相关的特征关联。该方法通过优化特征分布，生成与遗忘样本特征分布明显不同的合成样本，仅需单次训练周期即可取得良好效果。在多个面部识别数据集上的大量实验表明，本方法在遗忘能力和模型性能保留方面均显著优于当前最先进的机器遗忘方法。
原文摘要 · Abstract (English)
With the explosive growth of deep learning applications and increasing privacy concerns, the right to be forgotten has become a critical requirement in various AI industries. For example, given a facial recognition system, some individuals may wish to remove their personal data that might have been used in the training phase. Unfortunately, deep neural networks sometimes unexpectedly leak personal identities, making this removal challenging. While recent machine unlearning algorithms aim to enable models to forget specific data, we identify an unintended utility drop-correlation collapse-in which the essential correlations between image features and true labels weaken during the forgetting process. To address this challenge, we propose Distribution-Level Feature Distancing (DLFD), a novel method that efficiently forgets instances while preserving task-relevant feature correlations. Our method synthesizes data samples by optimizing the feature distribution to be distinctly different from that of forget samples, achieving effective results within a single training epoch. Through extensive experiments on facial recognition datasets, we demonstrate that our approach significantly outperforms state-of-the-art machine unlearning methods in both forgetting performance and model utility preservation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。