Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space
This addresses the problem of high-quality synthetic data generation for tabular datasets, which is incremental as it builds on existing diffusion and VAE methods.
The paper tackles the challenge of generating synthetic tabular data with mixed data types by introducing Tabsyn, a method that uses a diffusion model in a VAE latent space, resulting in error rate reductions of 86% and 67% for distribution and correlation estimations compared to baselines.
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.