TabTransGAN: A hybrid approach integrating GAN and transformer architectures for tabular data synthesis

Abstract

While generative adversarial networks (GANs) have made significant advancements in the fields of image and text generation, their application to tabular data synthesis faces distinct challenges since they fail to effectively capture tabular data semantics, which leads to suboptimal performance. To address this challenge, we propose TabTransGAN, a novel architecture that combines the power of Transformer models and GANs to recognize the semantic integrity and attribute information of tabular data with more accuracy. TabTransGAN also introduces position encoding for each column to improve dimension recognition and facilitate correlation capture. Experimental results on 5 real-world datasets show that TabTransGAN outperforms existing methods in various aspects such as synthesis quality, machine learning performance, and privacy preservation.