mlsanityData to 7 Oct 2026

Conditional GAN for timeseries generation

arXiv 2006.16477 ↗First posted 30 Jun 2020cs.LG stat.MLcited by 36

Not on the map. Why?

Abstract (arXiv)

It is abundantly clear that time dependent data is a vital source of information in the world. The challenge has been for applications in machine learning to gain access to a considerable amount of quality data needed for algorithm development and analysis. Modeling synthetic data using a Generative Adversarial Network (GAN) has been at the heart of providing a viable solution. Our work focuses on one dimensional times series and explores the few shot approach, which is the ability of an algorithm to perform well with limited data. This work attempts to ease the frustration by proposing a new architecture, Time Series GAN (TSGAN), to model realistic time series data. We evaluate TSGAN on 70 data sets from a benchmark time series database. Our results demonstrate that TSGAN performs better than the competition both quantitatively using the Frechet Inception Score (FID) metric, and qualitatively when classification is used as the evaluation criteria.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 9; 2023: 8; 2024: 7; 2025: 7; 2026: 3.

36 papers.

Sort:

By area:

  1. 2023Vector Quantized Time Series Generation with a Bidirectional Prior Modelcited by 49
  2. 2022Physics-Guided, Physics-Informed, and Physics-Encoded Neural Networks in Scientific Computingcited by 24
  3. 2023TSGBench: Time Series Generation Benchmarkcited by 24
  4. 2023NetDiffus: Network Traffic Generation by Diffusion Models through Time-Series Imagingcited by 18
  5. 2023Unsupervised Representation Learning for Time Series: A Reviewcited by 14
  6. 2023Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-artcited by 14
  7. 2024A Practical Guide to Sample-based Statistical Distances for Evaluating Generative Models in Sciencecited by 14
  8. 2023Data Augmentation for Time-Series Classification: An Extensive Empirical Study and Comprehensive Surveycited by 9
  9. 2024Review for Handling Missing Data with special missing mechanismcited by 7
  10. 2025Causal Time Series Generation via Diffusion Modelscited by 7
  11. 2025Towards Identifiability of Hierarchical Temporal Causal Representation Learningcited by 7
  12. 2023Time-Transformer: Integrating Local and Global Features for Better Time Series Generation (Extended Version)cited by 6
24 more
  1. 2025Forging Time Series with Language: A Large Language Model Approach to Synthetic Data Generationcited by 6
  2. 2024LatentQGAN: A Hybrid QGAN with Classical Convolutional Autoencodercited by 5
  3. 2021Time Series (re)sampling using Generative Adversarial Networkscited by 4
  4. 2022The Interplay of AI and Digital Twin: Bridging the Gap between Data-Driven and Model-Driven Approachescited by 4
  5. 2022Transformer-based conditional generative adversarial network for multivariate time series generationcited by 4
  6. 2022Leveraging Statistical Shape Priors in GAN-based ECG Synthesiscited by 4
  7. 2024Towards Controllable Time Series Generationcited by 4
  8. 2022Out-of-Distribution Detection in Time-Series Domain: A Novel Seasonal Ratio Scoring Approachcited by 3
  9. 2023Masked Generative Modeling with Enhanced Sampling Schemecited by 3
  10. 2024GANs Conditioning Methods: A Surveycited by 3
  11. 2025CTBench: Cryptocurrency Time Series Generation Benchmarkcited by 3
  12. 2024On the Use of Relative Validity Indices for Comparing Clustering Approachescited by 2
  13. 2022Data-Driven Modeling of Noise Time Series with Convolutional Generative Adversarial Networkscited by 1
  14. 2022Quantifying Quality of Class-Conditional Generative Models in Time-Series Domaincited by 1
  15. 2025Synthetic ALS-EEG Data Augmentation for ALS Diagnosis Using Conditional WGAN with Weight Clippingcited by 1
  16. 2021Wasserstein GAN: Deep Generation applied on Bitcoins financial time seriescited by 0
  17. 2022Simulating Network Paths with Recurrent Buffering Unitscited by 0
  18. 2022PhysioGAN: Training High Fidelity Generative Model for Physiological Sensor Readingscited by 0
  19. 2024Simulating realistic short tandem repeat capillary electrophoretic signal using a generative adversarial networkcited by 0
  20. 2025Fiaingen: A financial time series generative method matching real-world data qualitycited by 0
  21. 2025Handling Extreme Class Imbalance: Using GANs in Data Augmentation for Suicide Predictioncited by 0
  22. 2026Conditional Generative Framework with Peak-Aware Attention for Robust Chemical Detection under Interferencescited by 0
  23. 2026SRT: Super-Resolution for Time Series via Disentangled Rectified Flowcited by 0
  24. 2026A GAN-Based Framework for Robust Data Synthesis in Satellite Internet Observationscited by 0