ReTrack：通过重定向去噪轨迹实现扩散模型的数据遗忘
ReTrack: Data Unlearning in Diffusion Models through Redirecting the Denoising Trajectory
AI总结：
ReTrack通过重要性采样构建更高效的微调损失，重定向去噪轨迹向k近邻，实现高效数据遗忘并保持生成质量，实验显示在多个数据集上达到最佳性能平衡。
摘要：
扩散模型在生成高质量、多样化的图像方面表现出色，但存在训练数据记忆化问题，引发隐私和安全担忧。数据遗忘旨在通过移除特定数据的影响而不重新训练来缓解这一问题。我们提出了ReTrack，一种适用于扩散模型的高效数据遗忘方法。ReTrack通过重要性采样构建更高效的微调损失，并通过保留主导项来近似该损失。这产生了可解释的目标，将去噪轨迹重定向至k-最近邻，从而在保持生成质量的同时实现高效的遗忘。在MNIST T-Shirt、CelebA-HQ、CIFAR-10和Stable Diffusion数据集上的实验表明，ReTrack在遗忘强度和生成质量保持之间取得了最佳平衡，实现了最先进的性能。
英文摘要：
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.
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。
