给每段噪声打分，让扩散模型训练更高效
NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training
- 用元学习为每个噪声分配重要性分数，动态调整训练权重
- 在FFHQ和ImageNet上提升生成质量，节省约20%训练时间
- 适合想优化扩散模型训练效率的研究者和工程师
扩散模型在生成任务中表现卓越，但其训练通常将注入的噪声视为同等重要。本文挑战这一假设，提出NoiseRater——一种用于扩散模型训练中实例级噪声估值的元学习框架。通过设计一个基于数据和时间步的参数化噪声评分器，实现对噪声样本的重要性评估与自适应重加权。评分器采用双层优化训练，在内层完成扩散模型更新后，优化下游验证性能。为提升部署效率，进一步设计解耦的两阶段流程：元训练阶段使用软加权，标准训练阶段转为硬噪声选择。在FFHQ和ImageNet上的大量实验表明，并非所有噪声样本贡献相同，优先处理高信息量噪声可显著提升训练效率与生成质量。结果证明噪声估值是改进扩散模型训练的一个关键且未被充分探索的方向。
原文摘要 · Abstract (English)
Diffusion models have achieved remarkable success across a wide range of generative tasks, yet their training paradigm largely treats injected noise as uniformly informative. In this work, we challenge this assumption and introduce NoiseRater, a meta-learning framework for instance-level noise valuation in diffusion model training. We propose a parametric noise rater that assigns importance scores to individual noise realizations conditioned on data and timestep, enabling adaptive reweighting of the training objective. The rater is trained via bilevel optimization to improve downstream validation performance after inner-loop diffusion updates. To enable efficient deployment, we further design a decoupled two-stage pipeline that transitions from soft weighting during meta-training to hard noise selection during standard training. Extensive experiments on FFHQ and ImageNet demonstrate that not all noise samples contribute equally, and that prioritizing informative noise improves both training efficiency and generation quality. Our results establish noise valuation as a complementary and previously underexplored axis for improving diffusion model training. Our code is available at: https://anonymous.4open.science/r/NoiseRater-DEB116.
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。