Skip to yearly menu bar Skip to main content


Training Unbiased Diffusion Models From Biased Dataset

Yeongmin Kim · Byeonghu Na · Minsang Park · JoonHo Jang · Dongjun Kim · Wanmo Kang · Il-chul Moon

Halle B #48
[ ] [ Project Page ]
Thu 9 May 1:45 a.m. PDT — 3:45 a.m. PDT


With significant advancements in diffusion models, addressing the potential risks of dataset bias becomes increasingly important. Since generated outputs directly suffer from dataset bias, mitigating latent bias becomes a key factor in improving sample quality and proportion. This paper proposes time-dependent importance reweighting to mitigate the bias for the diffusion models. We demonstrate that the time-dependent density ratio becomes more precise than previous approaches, thereby minimizing error propagation in generative learning. While directly applying it to score-matching is intractable, we discover that using the time-dependent density ratio both for reweighting and score correction can lead to a tractable form of the objective function to regenerate the unbiased data density. Furthermore, we theoretically establish a connection with traditional score-matching, and we demonstrate its convergence to an unbiased distribution. The experimental evidence supports the usefulness of the proposed method, which outperforms baselines including time-independent importance reweighting on CIFAR-10, CIFAR-100, FFHQ, and CelebA with various bias settings. Our code is available at

Chat is not available.