mlsanityData to 14 Oct 2026

PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series

arXiv 2108.00981 ↗First posted 2 Aug 2021cs.LGcited by 58

Not on the map. Why?

Abstract (arXiv)

Realistic synthetic time series data of sufficient length enables practical applications in time series modeling tasks, such as forecasting, but remains a challenge. In this paper we present PSA-GAN, a generative adversarial network (GAN) that generates long time series samples of high quality using progressive growing of GANs and self-attention. We show that PSA-GAN can be used to reduce the error in two downstream forecasting tasks over baselines that only use real data. We also introduce a Frechet-Inception Distance-like score, Context-FID, assessing the quality of synthetic time series samples. In our downstream tasks, we find that the lowest scoring models correspond to the best-performing ones. Therefore, Context-FID could be a useful tool to develop time series GAN models.

Key facts. Cited by 58 papers in the map (data through 14 Oct 2026). Builds on 31 of its 48 references that are in the map. First posted on arXiv 2 Aug 2021.

Builds on

31 of 48 references.

References · 31

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  6. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  7. 2016Improved Techniques for Training GANscited by 2,970
  8. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  9. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  10. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  11. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  12. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
19 more
  1. 2016Least Squares Generative Adversarial Networkscited by 1,001
  2. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  3. 2018Self-Attention Generative Adversarial Networkscited by 809
  4. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 761
  5. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
  6. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 607
  7. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 519
  8. 2016Time Series Classification from Scratch with Deep Neural Networks: A Strong Baselinecited by 360
  9. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecastingcited by 337
  10. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 333
  11. 2019Unsupervised Scalable Representation Learning for Multivariate Time Seriescited by 269
  12. 2016C-RNN-GAN: Continuous recurrent neural networks with adversarial trainingcited by 132
  13. 2019GANSynth: Adversarial Neural Audio Synthesiscited by 116
  14. 2019Quant GANs: Deep Generation of Financial Time Seriescited by 108
  15. 2016Multi-Scale Convolutional Neural Networks for Time Series Classificationcited by 99
  16. 2020Meta-learning framework with applications to zero-shot time-series forecastingcited by 70
  17. 2017Adversarial Ranking for Language Generationcited by 50
  18. 2019GluonTS: Probabilistic Time Series Models in Pythoncited by 46
  19. 2020Decision-Aware Conditional GANs for Time Series Datacited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 6; 2024: 13; 2025: 24; 2026: 14.

58 papers.

Sort:

By area:

  1. 2023Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospectscited by 99
  2. 2023Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecastingcited by 88
  3. 2024Time Weaver: A Conditional Time Series Generation Modelcited by 37
  4. 2023TSGBench: Time Series Generation Benchmarkcited by 26
  5. 2024A Practical Guide to Sample-based Statistical Distances for Evaluating Generative Models in Sciencecited by 14
  6. 2025Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approachcited by 14
  7. 2024TimeLDM: Latent Diffusion Model for Unconditional Time Series Generationcited by 10
  8. 2025Deep Learning for Time Series Forecasting: A Surveycited by 10
  9. 2025Towards Identifiability of Hierarchical Temporal Causal Representation Learningcited by 9
  10. 2024Constrained Posterior Sampling: Time Series Generation with Hard Constraintscited by 7
  11. 2025A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Maskingcited by 7
  12. 2022Probabilistic Decomposition Transformer for Time Series Forecastingcited by 6
38 more
  1. 2023Time-Transformer: Integrating Local and Global Features for Better Time Series Generation (Extended Version)cited by 6
  2. 2024AIGC for Industrial Time Series: From Deep Generative Models to Large Generative Modelscited by 6
  3. 2024TimeBridge: Better Diffusion Prior Design with Bridge Models for Time Series Generationcited by 6
  4. 2024A Survey of Transformer Enabled Time Series Synthesiscited by 5
  5. 2024Denoising-Aware Contrastive Learning for Noisy Time Seriescited by 5
  6. 2024Towards Controllable Time Series Generationcited by 4
  7. 2024Bt-GAN: Generating Fair Synthetic Healthdata via Bias-transforming Generative Adversarial Networkscited by 4
  8. 2023GAT-GAN : A Graph-Attention-based Time-Series Generative Adversarial Networkcited by 3
  9. 2025CENTS: Generating synthetic electricity consumption time series for rare and unseen scenarioscited by 3
  10. 2025MSDformer: Multi-scale Discrete Transformer For Time Series Generationcited by 3
  11. 2025TimeWak: Temporal Chained-Hashing Watermark for Time Series Datacited by 3
  12. 2025CTBench: Cryptocurrency Time Series Generation Benchmarkcited by 3
  13. 2024zGAN: An Outlier-focused Generative Adversarial Network For Realistic Synthetic Data Generationcited by 2
  14. 2025A synthetic dataset of French electric load curves with temperature conditioningcited by 2
  15. 2025Sequence Modeling with Spectral Mean Flowscited by 2
  16. 2025TimeFlow: Towards Stochastic-Aware and Efficient Time Series Generation via Flow Matching Modelingcited by 2
  17. 2025TSGDiff: Rethinking Synthetic Time Series Generation from a Pure Graph Perspectivecited by 2
  18. 2025Towards Stable and Structured Time Series Generation with Perturbation-Aware Flow Matchingcited by 2
  19. 2025DiM-TS: Bridge the Gap between Selective State Space Models and Time Series for Generative Modelingcited by 2
  20. 2025TARFVAE: Efficient One-Step Generative Time Series Forecasting via TARFLOW based VAEcited by 2
  21. 2026TimeMar: Multi-Scale Autoregressive Modeling for Unconditional Time Series Generationcited by 2
  22. 2026Functional MRI Time Series Generation via Wavelet-Based Image Transform and Spectral Flow Matching for Brain Disorder Identificationcited by 2
  23. 2026E4GEN: Event-level Explainable Extreme-Enhanced Time-series Generationcited by 2
  24. 2024Federated Time Series Generation on Feature and Temporally Misaligned Datacited by 1
  25. 2025Time Series Similarity Score Functions to Monitor and Interact with the Training and Denoising Process of a Time Series Diffusion Model applied to a Human Activity Recognition Dataset based on IMUscited by 1
  26. 2025STEB: In Search of the Best Evaluation Approach for Synthetic Time Seriescited by 1
  27. 2025Stage-Diff: Stage-wise Long-Term Time Series Generation Based on Diffusion Modelscited by 1
  28. 2025DLGAN : Time Series Synthesis Based on Dual-Layer Generative Adversarial Networkscited by 1
  29. 2026TransConv-DDPM: Enhanced Diffusion Model for Generating Time-Series Data in Healthcarecited by 1
  30. 2026PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generationcited by 1
  31. 2023ResBit: Residual Bit Vector for Categorical Valuescited by 0
  32. 2024Deep Temporal Deaggregation: Large-Scale Spatio-Temporal Generative Modelscited by 0
  33. 2025Challenges and Limitations of Generative AI in Synthesizing Wearable Sensor Datacited by 0
  34. 2025CHIME: Conditional Hallucination and Integrated Multi-scale Enhancement for Time Series Diffusion Modelcited by 0
  35. 2025Diffusion-based translation between unpaired spontaneous premature neonatal EEG and fetal MEGcited by 0
  36. 2025Effective Series Decomposition and Components Learning for Time Series Generationcited by 0
  37. 2025SimDiff: Simpler Yet Better Diffusion Model for Time Series Point Forecastingcited by 0
  38. 2026Parallel Complex Diffusion for Scalable Time Series Generationcited by 0

50 most cited of 58 All 58 (JSON)