High-Quality Tabular Data Generation using Post-Selected VAE

TL;DR

This paper presents PSVAE, a simple yet effective variational autoencoder-based method for generating high-quality synthetic tabular data efficiently, addressing limitations of previous models in handling complex datasets.

Contribution

Introduction of PSVAE, a novel model combining loss optimization and post-selection to improve synthetic tabular data quality and runtime performance.

Findings

Produces high-quality synthetic data efficiently

Handles complex datasets better than previous models

Compensates for underrepresented categories

Abstract

Synthetic tabular data is becoming a necessity as concerns about data privacy intensify in the world. Tabular data can be useful for testing various systems, simulating real data, analyzing the data itself or building predictive models. Unfortunately, such data may not be available due to confidentiality issues. Previous techniques, such as TVAE (Xu et al., 2019) or OCTGAN (Kim et al., 2021), are either unable to handle particularly complex datasets, or are complex in themselves, resulting in inferior run time performance. This paper introduces PSVAE, a new simple model that is capable of producing high-quality synthetic data in less run time. PSVAE incorporates two key ideas: loss optimization and post-selection. Along with these ideas, the proposed model compensates for underrepresented categories and uses a modern activation function, Mish (Misra, 2019).