ciDATGAN: Conditional Inputs for Tabular GANs

TL;DR

ciDATGAN introduces a novel conditional input methodology for tabular GANs, enabling better data unbiasing and dataset completion by learning underlying data logic, inspired by image completion techniques.

Contribution

It presents ciDATGAN, an evolution of DATGAN, incorporating conditional inputs to improve dataset unbiasing and completion in tabular data generation.

Findings

Conditional inputs can unbias datasets effectively.

ciDATGAN can learn data logic for dataset completion.

Model performance is affected by added conditional inputs.

Abstract

Conditionality has become a core component for Generative Adversarial Networks (GANs) for generating synthetic images. GANs are usually using latent conditionality to control the generation process. However, tabular data only contains manifest variables. Thus, latent conditionality either restricts the generated data or does not produce sufficiently good results. Therefore, we propose a new methodology to include conditionality in tabular GANs inspired by image completion methods. This article presents ciDATGAN, an evolution of the Directed Acyclic Tabular GAN (DATGAN) that has already been shown to outperform state-of-the-art tabular GAN models. First, we show that the addition of conditional inputs does hinder the model's performance compared to its predecessor. Then, we demonstrate that ciDATGAN can be used to unbias datasets with the help of well-chosen conditional inputs. Finally, it shows that ciDATGAN can learn the logic behind the data and, thus, be used to complete large synthetic datasets using data from a smaller feeder dataset.