Balanced Mixed-Type Tabular Data Synthesis with Diffusion Models

arXiv:2404.08254v1 Announce Type: new
Abstract: Diffusion models have emerged as a robust framework for various generative tasks, such as image and audio synthesis, and have also demonstrated a remarkable ability to generate mixed-type tabular data comprising both continuous and discrete variables. However, current approaches to training diffusion models on mixed-type tabular data tend to inherit the imbalanced distributions of features present in the training dataset, which can result in biased sampling. In this research, we introduce a fair diffusion model …

abstract arxiv audio audio synthesis continuous cs.lg current data diffusion diffusion models framework generate generative however image mixed robust synthesis tabular tabular data tasks training type variables