Risk-Sensitive Diffusion: Robustly Optimizing Diffusion Models with Noisy Samples

TL;DR

This paper introduces risk-sensitive SDEs to enhance the robustness of diffusion models when trained on noisy, non-image data, demonstrating improved performance across various datasets.

Contribution

It proposes a novel risk-sensitive SDE framework that accounts for data quality, enabling diffusion models to better handle noisy samples in non-image data.

Findings

Risk-sensitive SDE effectively mitigates noise effects.

Significant performance improvements over baselines.

Applicable to tabular and time-series data.

Abstract

Diffusion models are mainly studied on image data. However, non-image data (e.g., tabular data) are also prevalent in real applications and tend to be noisy due to some inevitable factors in the stage of data collection, degrading the generation quality of diffusion models. In this paper, we consider a novel problem setting where every collected sample is paired with a vector indicating the data quality: risk vector. This setting applies to many scenarios involving noisy data and we propose risk-sensitive SDE, a type of stochastic differential equation (SDE) parameterized by the risk vector, to address it. With some proper coefficients, risk-sensitive SDE can minimize the negative effect of noisy samples on the optimization of diffusion models. We conduct systematic studies for both Gaussian and non-Gaussian noise distributions, providing analytical forms of risk-sensitive SDE. To verify the effectiveness of our method, we have conducted extensive experiments on multiple tabular and time-series datasets, showing that risk-sensitive SDE permits a robust optimization of diffusion models with noisy samples and significantly outperforms previous baselines.