提出高效精准的扩散模型数据遗忘方法，训练速度更快且效果不降。
PECKER: A Precisely Efficient Critical Knowledge Erasure Recipe For Machine Unlearning in Diffusion Models
- 用显著性掩码聚焦关键参数更新，减少无效计算。
- 在CIFAR-10和STL-10上实现更快的类别与概念遗忘。
- 适合需要快速合规删数据的生成式AI应用。
机器遗忘（MU）已成为生成式AI模型安全合规运行的关键技术。现有方法虽有效，但普遍带来高昂的训练时间和计算开销。我们分析发现，问题根源在于梯度更新方向不佳，导致训练效率低且收敛不稳定。为此，提出PECKER方法，在蒸馏框架中引入显著性掩码，优先更新对目标数据遗忘贡献最大的参数，从而减少不必要的梯度计算，显著缩短训练时间，同时保持遗忘效果。实验表明，该方法在CIFAR-10和STL-10数据集上能更快速生成已遗忘特定类别或概念的样本，且生成图像分布与真实分布高度一致，实现类别遗忘和概念遗忘的双重加速。
原文摘要 · Abstract (English)
Machine unlearning (MU) has become a critical technique for GenAI models' safe and compliant operation. While existing MU methods are effective, most impose prohibitive training time and computational overhead. Our analysis suggests the root cause lies in poorly directed gradient updates, which reduce training efficiency and destabilize convergence. To mitigate these issues, we propose PECKER, an efficient MU approach that matches or outperforms prevailing methods. Within a distillation framework, PECKER introduces a saliency mask to prioritize updates to parameters that contribute most to forgetting the targeted data, thereby reducing unnecessary gradient computation and shortening overall training time without sacrificing unlearning efficacy. Our method generates samples that unlearn related class or concept more quickly, while closely aligning with the true image distribution on CIFAR-10 and STL-10 datasets, achieving shorter training times for both class forgetting and concept forgetting.
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。