mlsanityData to 14 Oct 2026

A Survey of Transformer Enabled Time Series Synthesis

arXiv 2406.02322 ↗First posted 4 Jun 2024cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Generative AI has received much attention in the image and language domains, with the transformer neural network continuing to dominate the state of the art. Application of these models to time series generation is less explored, however, and is of great utility to machine learning, privacy preservation, and explainability research. The present survey identifies this gap at the intersection of the transformer, generative AI, and time series data, and reviews works in this sparsely populated subdomain. The reviewed works show great variety in approach, and have not yet converged on a conclusive answer to the problems the domain poses. GANs, diffusion models, state space models, and autoencoders were all encountered alongside or surrounding the transformers which originally motivated the survey. While too open a domain to offer conclusive insights, the works surveyed are quite suggestive, and several recommendations for best practice, and suggestions of valuable future work, are provided.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 61 of its 102 references that are in the map. First posted on arXiv 4 Jun 2024.

Builds on

61 of 102 references.

References · 61

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  6. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  7. 2022Generative Adversarial Networkscited by 5,627
  8. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  9. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  10. 2017Improved Training of Wasserstein GANscited by 2,235
  11. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  12. 2014Conditional Generative Adversarial Netscited by 2,162
38 more
  1. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  2. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  3. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  4. 2020On Layer Normalization in the Transformer Architecturecited by 922
  5. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  6. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 761
  7. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 700
  8. 2023A decoder-only foundation model for time-series forecastingcited by 692
  9. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
  10. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 565
  11. 2022Transformers in Time Series: A Surveycited by 497
  12. 2014Semi-Supervised Learning with Deep Generative Modelscited by 496
  13. 2016Tutorial on Variational Autoencoderscited by 409
  14. 2015Adversarial Autoencoderscited by 364
  15. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 333
  16. 2021Monash Time Series Forecasting Archivecited by 267
  17. 2023A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPTcited by 224
  18. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 198
  19. 2019Sparse Sequence-to-Sequence Modelscited by 170
  20. 2021TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Upcited by 162
  21. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  22. 2020An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networkscited by 128
  23. 2020Deep Learning for Time Series Forecasting: Tutorial and Literature Surveycited by 117
  24. 2023Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlookcited by 110
  25. 2019Quant GANs: Deep Generation of Financial Time Seriescited by 108
  26. 2021Darts: User-Friendly Modern Machine Learning for Time Seriescited by 91
  27. 2013Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networkscited by 84
  28. 2022A General Survey on Attention Mechanisms in Deep Learningcited by 64
  29. 2021PSA-GAN: Progressive Self Attention GANs for Synthetic Time Seriescited by 58
  30. 2016UniMiB SHAR: a new dataset for human activity recognition using acceleration data from smartphonescited by 54
  31. 2023On the Constrained Time-Series Generation Problemcited by 54
  32. 2022Transformers in Time-series Analysis: A Tutorialcited by 46
  33. 2022TTS-GAN: A Transformer-based Time-Series Generative Adversarial Networkcited by 41
  34. 2022Data Augmentation techniques in time series domain: A survey and taxonomycited by 41
  35. 2022Efficient Long Sequence Modeling via State Space Augmented Transformercited by 37
  36. 2024Time Weaver: A Conditional Time Series Generation Modelcited by 37
  37. 2023Diffusion-based Conditional ECG Generation with Structured State Space Modelscited by 36
  38. 2021Temporal Latent Auto-Encoder: A Method for Probabilistic Multivariate Time Series Forecastingcited by 32

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 1.

5 papers.

  1. 2025How to Unlock Time Series Editing? Diffusion-Driven Approach with Multi-Grained Controlcited by 1
  2. 2025Instruction-based Time Series Editingcited by 1
  3. 2025Univariate to Multivariate: LLMs as Zero-Shot Predictors for Time-Series Forecastingcited by 0
  4. 2025Privacy-Preserving Generative Modeling and Clinical Validation of Longitudinal Health Records for Chronic Diseasecited by 0
  5. 2026Continuous-Time Machine Learning: A Unified Mathematical Perspectivecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series
  2. 2025Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach
  3. 2026World Machine: Towards Generative World Modeling for Time-Series
  4. 2026DiTS: Multimodal Diffusion Transformers Are Time Series Forecasters
  5. 2026Towards a Unified Generative Model for Scarce Time Series with Domain Experts
  6. 2024TimeLDM: Latent Diffusion Model for Unconditional Time Series Generation
  7. 2025A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Masking
  8. 2025Towards Time Series Generation Conditioned on Unstructured Natural Language