Fair Sampling in Diffusion Models through Switching Mechanism
This addresses fairness issues in generative AI for applications requiring unbiased data, but it is incremental as it builds on existing sampling control methods.
The paper tackles the problem of amplified bias in diffusion models by proposing an attribute switching mechanism for fairness-aware sampling, achieving fair data generation and preserving utility without additional training.
Diffusion models have shown their effectiveness in generation tasks by well-approximating the underlying probability distribution. However, diffusion models are known to suffer from an amplified inherent bias from the training data in terms of fairness. While the sampling process of diffusion models can be controlled by conditional guidance, previous works have attempted to find empirical guidance to achieve quantitative fairness. To address this limitation, we propose a fairness-aware sampling method called \textit{attribute switching} mechanism for diffusion models. Without additional training, the proposed sampling can obfuscate sensitive attributes in generated data without relying on classifiers. We mathematically prove and experimentally demonstrate the effectiveness of the proposed method on two key aspects: (i) the generation of fair data and (ii) the preservation of the utility of the generated data.