Generative adversarial networks in time series: A survey and taxonomy

TL;DR

This survey reviews recent developments in GANs for time series data, categorizing variants, discussing architectures, applications, evaluation metrics, privacy concerns, and future directions.

Contribution

It provides a comprehensive taxonomy of GAN variants for time series, summarizing recent literature, and discussing evaluation and privacy considerations.

Findings

Taxonomy of discrete and continuous GAN variants for time series

Summary of architectures, results, and applications in recent literature

Discussion of evaluation metrics and privacy measures

Abstract

Generative adversarial networks (GANs) studies have grown exponentially in the past few years. Their impact has been seen mainly in the computer vision field with realistic image and video manipulation, especially generation, making significant advancements. While these computer vision advances have garnered much attention, GAN applications have diversified across disciplines such as time series and sequence generation. As a relatively new niche for GANs, fieldwork is ongoing to develop high quality, diverse and private time series data. In this paper, we review GAN variants designed for time series related applications. We propose a taxonomy of discrete-variant GANs and continuous-variant GANs, in which GANs deal with discrete time series and continuous time series data. Here we showcase the latest and most popular literature in this field; their architectures, results, and applications. We also provide a list of the most popular evaluation metrics and their suitability across applications. Also presented is a discussion of privacy measures for these GANs and further protections and directions for dealing with sensitive data. We aim to frame clearly and concisely the latest and state-of-the-art research in this area and their applications to real-world technologies.