Generating Benchmark Health Data Using a Tabular Diffusion Transformer

Hao Yan, Lisa Pilgram, Dan Liu, Linglong Kong, Fida Dankar et al.|August 14, 2026arXiv

Key Takeaway

You can now generate realistic synthetic tabular health data from multiple heterogeneous sources by standardizing them statistically first, then using diffusion transformers to learn and reproduce their patterns.

Summary

This paper presents a method for generating synthetic health data from multiple different database tables with varying structures. It works in two stages: first converting diverse tables into a standardized statistical format, then using a diffusion transformer to learn patterns and generate new synthetic tables.

data architecture evaluation

Key Terms

diffusion-models synthetic-data tabular-data heterogeneous-data transformer-architecture