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

arXiv: https://arxiv.org/abs/2108.00981 · HTML: https://mlsanity.com/paper/2108.00981/

## 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 (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks](https://mlsanity.com/paper/1704.04110/) (2017)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://mlsanity.com/paper/1703.07015/) (2017)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://mlsanity.com/paper/1912.09363/) (2019)
- [N-BEATS: Neural basis expansion analysis for interpretable time series forecasting](https://mlsanity.com/paper/1905.10437/) (2019)
- [Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting](https://mlsanity.com/paper/1907.00235/) (2019)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://mlsanity.com/paper/1611.06455/) (2016)
- [Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2101.12072/) (2021)
- [Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs](https://mlsanity.com/paper/1706.02633/) (2017)
- [Unsupervised Scalable Representation Learning for Multivariate Time Series](https://mlsanity.com/paper/1901.10738/) (2019)
- [C-RNN-GAN: Continuous recurrent neural networks with adversarial training](https://mlsanity.com/paper/1611.09904/) (2016)
- [GANSynth: Adversarial Neural Audio Synthesis](https://mlsanity.com/paper/1902.08710/) (2019)
- [Quant GANs: Deep Generation of Financial Time Series](https://mlsanity.com/paper/1907.06673/) (2019)
- [Multi-Scale Convolutional Neural Networks for Time Series Classification](https://mlsanity.com/paper/1603.06995/) (2016)
- [Meta-learning framework with applications to zero-shot time-series forecasting](https://mlsanity.com/paper/2002.02887/) (2020)
- [Adversarial Ranking for Language Generation](https://mlsanity.com/paper/1705.11001/) (2017)
- [GluonTS: Probabilistic Time Series Models in Python](https://mlsanity.com/paper/1906.05264/) (2019)

## Built on by (most cited first, 30 of 58)

- [Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects](https://mlsanity.com/paper/2306.10125/) (2023)
- [Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2307.11494/) (2023)
- [Time Weaver: A Conditional Time Series Generation Model](https://mlsanity.com/paper/2403.02682/) (2024)
- [TSGBench: Time Series Generation Benchmark](https://mlsanity.com/paper/2309.03755/) (2023)
- [A Practical Guide to Sample-based Statistical Distances for Evaluating Generative Models in Science](https://mlsanity.com/paper/2403.12636/) (2024)
- [Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach](https://mlsanity.com/paper/2505.20446/) (2025)
- [TimeLDM: Latent Diffusion Model for Unconditional Time Series Generation](https://mlsanity.com/paper/2407.04211/) (2024)
- [Deep Learning for Time Series Forecasting: A Survey](https://mlsanity.com/paper/2503.10198/) (2025)
- [Towards Identifiability of Hierarchical Temporal Causal Representation Learning](https://mlsanity.com/paper/2510.18310/) (2025)
- [Constrained Posterior Sampling: Time Series Generation with Hard Constraints](https://mlsanity.com/paper/2410.12652/) (2024)
- [A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Masking](https://mlsanity.com/paper/2510.06699/) (2025)
- [Probabilistic Decomposition Transformer for Time Series Forecasting](https://mlsanity.com/paper/2210.17393/) (2022)
- [Time-Transformer: Integrating Local and Global Features for Better Time Series Generation (Extended Version)](https://mlsanity.com/paper/2312.11714/) (2023)
- [AIGC for Industrial Time Series: From Deep Generative Models to Large Generative Models](https://mlsanity.com/paper/2407.11480/) (2024)
- [TimeBridge: Better Diffusion Prior Design with Bridge Models for Time Series Generation](https://mlsanity.com/paper/2408.06672/) (2024)
- [A Survey of Transformer Enabled Time Series Synthesis](https://mlsanity.com/paper/2406.02322/) (2024)
- [Denoising-Aware Contrastive Learning for Noisy Time Series](https://mlsanity.com/paper/2406.04627/) (2024)
- [Towards Controllable Time Series Generation](https://mlsanity.com/paper/2403.03698/) (2024)
- [Bt-GAN: Generating Fair Synthetic Healthdata via Bias-transforming Generative Adversarial Networks](https://mlsanity.com/paper/2404.13634/) (2024)
- [GAT-GAN : A Graph-Attention-based Time-Series Generative Adversarial Network](https://mlsanity.com/paper/2306.01999/) (2023)
- [CENTS: Generating synthetic electricity consumption time series for rare and unseen scenarios](https://mlsanity.com/paper/2501.14426/) (2025)
- [MSDformer: Multi-scale Discrete Transformer For Time Series Generation](https://mlsanity.com/paper/2505.14202/) (2025)
- [TimeWak: Temporal Chained-Hashing Watermark for Time Series Data](https://mlsanity.com/paper/2506.06407/) (2025)
- [CTBench: Cryptocurrency Time Series Generation Benchmark](https://mlsanity.com/paper/2508.02758/) (2025)
- [zGAN: An Outlier-focused Generative Adversarial Network For Realistic Synthetic Data Generation](https://mlsanity.com/paper/2410.20808/) (2024)
- [A synthetic dataset of French electric load curves with temperature conditioning](https://mlsanity.com/paper/2504.14046/) (2025)
- [Sequence Modeling with Spectral Mean Flows](https://mlsanity.com/paper/2510.15366/) (2025)
- [TimeFlow: Towards Stochastic-Aware and Efficient Time Series Generation via Flow Matching Modeling](https://mlsanity.com/paper/2511.07968/) (2025)
- [TSGDiff: Rethinking Synthetic Time Series Generation from a Pure Graph Perspective](https://mlsanity.com/paper/2511.12174/) (2025)
- [Towards Stable and Structured Time Series Generation with Perturbation-Aware Flow Matching](https://mlsanity.com/paper/2511.14488/) (2025)

## 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.