通过调整去噪步骤的采样策略，实现对扩散模型记忆性的精准控制。
Memorization Control in Diffusion Models from Denoising-centric Perspective
- 从去噪视角出发，发现均匀采样导致学习不均衡
- 调整置信区间宽度，可直接调控记忆与泛化的平衡
- 在图像和一维信号生成中均降低记忆，提升分布匹配度
控制扩散模型中的记忆现象对于需要生成数据紧密匹配训练分布的应用至关重要。现有方法主要聚焦于数据或模型中心的修改，将扩散模型视为独立预测器。本文从去噪中心视角研究扩散模型的记忆性，发现均匀时间步采样会导致不同去噪步骤的学习贡献不均，因信噪比差异而偏向记忆。为此，我们提出一种显式控制学习发生位置的时间步采样策略，通过调节置信区间的宽度，直接调控记忆与泛化的权衡。在图像和1D信号生成任务上的实验表明，将学习重点移向后期去噪步骤能持续降低记忆并改善与训练数据的分布对齐，验证了该方法的通用性与有效性。
原文摘要 · Abstract (English)
Controlling memorization in diffusion models is critical for applications that require generated data to closely match the training distribution. Existing approaches mainly focus on data centric or model centric modifications, treating the diffusion model as an isolated predictor. In this paper, we study memorization in diffusion models from a denoising centric perspective. We show that uniform timestep sampling leads to unequal learning contributions across denoising steps due to differences in signal to noise ratio, which biases training toward memorization. To address this, we propose a timestep sampling strategy that explicitly controls where learning occurs along the denoising trajectory. By adjusting the width of the confidence interval, our method provides direct control over the memorization generalization trade off. Experiments on image and 1D signal generation tasks demonstrate that shifting learning emphasis toward later denoising steps consistently reduces memorization and improves distributional alignment with training data, validating the generality and effectiveness of our approach.
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。