An improved tabular data generator with VAE-GMM integration

arXiv:2404.08434v1 Announce Type: new
Abstract: The rising use of machine learning in various fields requires robust methods to create synthetic tabular data. Data should preserve key characteristics while addressing data scarcity challenges. Current approaches based on Generative Adversarial Networks, such as the state-of-the-art CTGAN model, struggle with the complex structures inherent in tabular data. These data often contain both continuous and discrete features with non-Gaussian distributions. Therefore, we propose a novel Variational Autoencoder (VAE)-based model that addresses these limitations. Inspired …

abstract adversarial art arxiv challenges create cs.ai cs.lg current data fields generative generative adversarial networks generator integration key machine machine learning networks robust state struggle synthetic tabular tabular data type vae