Synthesizing Tabular Data using Generative Adversarial Networks

TL;DR

This paper introduces TGAN, a GAN-based model capable of generating high-quality synthetic tabular data, effectively capturing complex correlations and scaling well for large datasets, useful for privacy and data augmentation.

Contribution

The paper presents TGAN, a novel GAN architecture specifically designed for generating realistic tabular data with mixed variable types, outperforming traditional models.

Findings

TGAN outperforms statistical models in capturing column correlations.

TGAN scales effectively to large datasets.

TGAN produces high-quality synthetic tabular data.

Abstract

Generative adversarial networks (GANs) implicitly learn the probability distribution of a dataset and can draw samples from the distribution. This paper presents, Tabular GAN (TGAN), a generative adversarial network which can generate tabular data like medical or educational records. Using the power of deep neural networks, TGAN generates high-quality and fully synthetic tables while simultaneously generating discrete and continuous variables. When we evaluate our model on three datasets, we find that TGAN outperforms conventional statistical generative models in both capturing the correlation between columns and scaling up for large datasets.