Generative adversarial networks in time series: A survey and taxonomy

2021/07/23 by Eoin Brophy, Zhengwei Wang, Brophy, Eoin +6 · 46 citations
Computer Science · #Adversarial system #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #Artificial intelligence #Computer science #Data science #Deep learning #Digital Media Forensic Detection #FOS: Computer and information sciences #Field (mathematics) #Generative Adversarial Networks and Image Synthesis #Generative adversarial network #Generative grammar #Machine Learning (cs.LG) #Machine learning #Series (stratigraphy) #Taxonomy (biology) #Time series #cs.AI #cs.LG

paper · pdf · doi:10.48550/arxiv.2107.11098

published in arXiv (Cornell University) (Cornell University)

arxiv created 2021/07/23 · openalex publication_date 2021/07/23 · arxiv updated 2021/07/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Generalized autoregressive conditional heteroskedasticity
• A Survey on Transfer Learning
• Generating images with recurrent adversarial networks
• Generative Adversarial Text to Image Synthesis
• C-RNN-GAN: Continuous recurrent neural networks with adversarial training
• Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy
• Boundary-Seeking Generative Adversarial Networks
• Generating Multi-label Discrete Patient Records using Generative Adversarial Networks
• Synthetic Medical Images from Dual Generative Adversarial Networks
• Health Data in an Open World
• Differentially Private Generative Adversarial Network
• Quick and Easy Time Series Generation with Established Image-based GANs
• Differential Privacy
• Snore-GANs: Improving Automatic Snore Sound Classification with Synthesized Data
• Synthesis of Realistic ECG using Generative Adversarial Networks
• MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• FedGAN: Federated Generative Adversarial Networks for Distributed Data
• Decision-Aware Conditional GANs for Time Series Data
• Learning Multiple Layers of Features from Tiny Images

Cited by

• MSDformer: Multi-scale Discrete Transformer For Time Series Generation

Related

• ChronoGAN: Supervised and Embedded Generative Adversarial Networks for Time Series Generation
• GAT-GAN : A Graph-Attention-based Time-Series Generative Adversarial Network
• DLGAN : Time Series Synthesis Based on Dual-Layer Generative Adversarial Networks
• Quick and Easy Time Series Generation with Established Image-based GANs
• SeriesGAN: Time Series Generation via Adversarial and Autoregressive Learning