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

TL;DR

Tabsyn introduces a novel diffusion-based approach within a VAE latent space to generate high-quality, fast, and versatile synthetic tabular data across diverse data types and complex inter-column relations.

Contribution

The paper presents Tabsyn, a new method that effectively synthesizes tabular data by combining diffusion models with a VAE in a unified latent space, handling various data types and relations.

Findings

Outperforms existing methods on six datasets

Reduces distribution error rates by up to 86%

Generates data faster with fewer reverse steps

Abstract

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 capture 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.