Skip to yearly menu bar Skip to main content


Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space

Hengrui Zhang · Jiani Zhang · Zhengyuan Shen · Balasubramaniam Srinivasan · Xiao Qin · Christos Faloutsos · Huzefa Rangwala · George Karypis

Halle A 8 - 9
[ ] [ Visit Oral 8A ]
Fri 10 May 7 a.m. — 7:15 a.m. PDT


Recent advances in tabular data generation have greatly enhanced synthetic data quality. However, extending diffusion models to tabular data is challenging due to the intricately varied distributions and a blend of data types of tabular data. This paper introduces TabSyn, a methodology that synthesizes tabular data by leveraging a diffusion model within a variational autoencoder (VAE) crafted latent space. The key advantages of the proposed Tabsyn include (1) Generality: the ability to handle a broad spectrum of data types by converting them into a single unified space and explicitly capturing inter-column relations; (2) Quality: optimizing the distribution of latent embeddings to enhance the subsequent training of diffusion models, which helps generate high-quality synthetic data; (3) Speed: much fewer number of reverse steps and faster synthesis speed than existing diffusion-based methods. Extensive experiments on six datasets with five metrics demonstrate that Tabsyn outperforms existing methods. Specifically, it reduces the error rates by 86% and 67% for column-wise distribution and pair-wise column correlation estimations compared with the most competitive baselines. The code has been made available at

Chat is not available.