通过重定向去噪轨迹，快速清除扩散模型中的特定数据记忆。
ReTrack: Data Unlearning in Diffusion Models through Redirecting the Denoising Trajectory
- 用重要性采样构建高效微调损失，仅保留关键项。
- 在多个数据集上实现最强去记忆效果，生成质量保持良好。
- 适合需要快速移除隐私数据的扩散模型应用。
扩散模型虽能生成高质量、多样化的图像，但存在训练数据记忆问题，引发严重的隐私与安全担忧。数据去记忆方法旨在移除特定数据的影响，而无需从头训练。本文提出 ReTrack，一种针对扩散模型的快速有效去记忆方法。ReTrack 采用重要性采样构建更高效的微调损失，并通过仅保留主导项来近似该损失，得到可解释的目标函数，从而引导去噪轨迹向 $k$-最近邻方向转移，实现高效去记忆同时保持生成质量。在 MNIST T-Shirt、CelebA-HQ、CIFAR-10 和 Stable Diffusion 上的实验表明，ReTrack 达到当前最优性能，在去记忆强度与生成质量之间取得最佳平衡。
原文摘要 · Abstract (English)
Diffusion models excel at generating high-quality, diverse images but suffer from training data memorization, raising critical privacy and safety concerns. Data unlearning has emerged to mitigate this issue by removing the influence of specific data without retraining from scratch. We propose ReTrack, a fast and effective data unlearning method for diffusion models. ReTrack employs importance sampling to construct a more efficient fine-tuning loss, which we approximate by retaining only dominant terms. This yields an interpretable objective that redirects denoising trajectories toward the $k$-nearest neighbors, enabling efficient unlearning while preserving generative quality. Experiments on MNIST T-Shirt, CelebA-HQ, CIFAR-10, and Stable Diffusion show that ReTrack achieves state-of-the-art performance, striking the best trade-off between unlearning strength and generation quality 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。