A Comprehensive Survey on Generative Diffusion Models for Structured Data
This is an incremental contribution that synthesizes existing research to promote developments in generative diffusion models for structured data, which are less studied compared to visual and textual data.
This paper addresses the lack of literature and reviews on generative diffusion models for structured data, such as tabular and time series data, by providing a comprehensive survey that overviews theory, describes existing works, and discusses limitations and future directions.
In recent years, generative diffusion models have achieved a rapid paradigm shift in deep generative models by showing groundbreaking performance across various applications. Meanwhile, structured data, encompassing tabular and time series data, has been received comparatively limited attention from the deep learning research community, despite its omnipresence and extensive applications. Thus, there is still a lack of literature and its reviews on structured data modelling via diffusion models, compared to other data modalities such as visual and textual data. To address this gap, we present a comprehensive review of recently proposed diffusion models in the field of structured data. First, this survey provides a concise overview of the score-based diffusion model theory, subsequently proceeding to the technical descriptions of the majority of pioneering works that used structured data in both data-driven general tasks and domain-specific applications. Thereafter, we analyse and discuss the limitations and challenges shown in existing works and suggest potential research directions. We hope this review serves as a catalyst for the research community, promoting developments in generative diffusion models for structured data.