Generative models for tabular data: A review

Generative design refers to a methodology that not only simulates the characteristics of a given data or system but also creates artificial data for various purposes. It’s a significant research area encompassing diverse issues such as privacy preservation, data distribution analysis, and the development of surrogate models. Initially, research in this field primarily employed stochastic models or basic machine learning methods. However, with the advancement of deep learning technology, numerous studies have emerged, showcasing developed mechanisms using artificial neural network-based methods like variational autoencoders (VAEs) and generative adversarial networks (GANs). These studies extend across different data types, including images and texts, tailored to specific objectives. This paper presents a systematic review of generative design research focused on tabular data. We begin by elucidating the characteristics of tabular data within generative design, followed by a discussion on the goals and challenges in this area. Subsequently, the paper introduces various generative design studies on tabular data, categorized according to their methodological development and unique objectives. Finally, we address the benchmark methods used in generative design for tabular and how their performance is evaluated.