用参考数据集让模型忘记特定数据，效果更稳定可靠。
Reference-Guided Machine Unlearning
- 以独立数据集为参考，引导模型在遗忘数据上表现像从未见过一样。
- 在多种模型和数据集上，遗忘效果优于现有方法，且不影响通用性能。
- 适合需要安全删除数据的场景，如隐私保护或合规需求。
机器遗忘旨在移除特定数据对训练模型的影响，同时保持模型的通用能力。现有近似遗忘方法通常依赖性能下降的启发式信号，如损失最大化或随机标签，但这些信号条件不佳，导致优化不稳定，损害模型泛化能力。我们主张遗忘应优先考虑分布不可区分性，使模型在被遗忘数据上的行为与对真正未见数据的行为一致。基于此，我们提出参考引导遗忘（ReGUn），利用一个独立保留的数据集提供有原则的、类别条件化的参考进行知识蒸馏。我们在多种模型架构、自然图像数据集及不同遗忘比例下验证，ReGUn始终优于标准近似基线，实现更优的遗忘-效用权衡。
原文摘要 · Abstract (English)
Machine unlearning aims to remove the influence of specific data from trained models while preserving general utility. Existing approximate unlearning methods often rely on performance-degradation heuristics, such as loss maximization or random labeling. However, these signals can be poorly conditioned, leading to unstable optimization and harming the model's generalization. We argue that unlearning should instead prioritize distributional indistinguishability, aligning the model's behavior on forget data with its behavior on truly unseen data. Motivated by this, we propose Reference-Guided Unlearning (ReGUn), a framework that leverages a disjoint held-out dataset to provide a principled, class-conditioned reference for distillation. We demonstrate across various model architectures, natural image datasets, and varying forget fractions that ReGUn consistently outperforms standard approximate baselines, achieving a superior forgetting-utility trade-off.
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。