通过动态调整噪声水平权重，提升扩散模型训练稳定性与生成质量。
Variance-Aware Adaptive Weighting for Diffusion Model Training
- 根据噪声水平的损失方差动态调整训练权重
- 在CIFAR-10/100上实现更低FID与更小随机种子差异
- 适合关注训练稳定性和生成性能优化的研究者
扩散模型在生成建模中取得显著成功，但不同噪声水平下的训练动态严重失衡，导致优化效率低且学习过程不稳定。本文从对数信噪比（log-SNR）水平上的损失方差角度分析该问题，提出一种方差感知的自适应加权策略。该方法基于观测到的方差分布动态调整训练权重，促进各噪声水平间更均衡的优化过程。在CIFAR-10和CIFAR-100上的大量实验表明，该方法在标准训练基础上持续提升生成性能，实现更低的弗雷切特初始距离（FID），同时降低不同随机种子间的性能波动。额外分析包括损失-对数信噪比可视化、方差热图及消融实验，进一步验证了自适应加权能有效稳定训练动态。这些结果凸显了方差感知训练策略在改善扩散模型优化方面的潜力。
原文摘要 · Abstract (English)
Diffusion models have recently achieved remarkable success in generative modeling, yet their training dynamics across different noise levels remain highly imbalanced, which can lead to inefficient optimization and unstable learning behavior. In this work, we investigate this imbalance from the perspective of loss variance across log-SNR levels and propose a variance-aware adaptive weighting strategy to address it. The proposed approach dynamically adjusts training weights based on the observed variance distribution, encouraging a more balanced optimization process across noise levels. Extensive experiments on CIFAR-10 and CIFAR-100 demonstrate that the proposed method consistently improves generative performance over standard training schemes, achieving lower Fréchet Inception Distance (FID) while also reducing performance variance across random seeds. Additional analysis, including loss-log-SNR visualization, variance heatmaps, and ablation studies, further reveal that the adaptive weighting effectively stabilizes training dynamics. These results highlight the potential of variance-aware training strategies for improving diffusion model optimization.
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。