mlsanityData to 7 Oct 2026

DAD4TS: Data-Augmentation-Oriented Diffusion Model for Time-Series Forecasting with Small-Scale Data

arXiv 2605.17866 ↗First posted 18 May 2026cs.LGcited by 0

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Small-scale data is a critical problem in time-series forecasting tasks. Data augmentation is an effective strategy for this task, but it has a limitation in generating meaningful data. To address this limitation, we propose DAD4TS, a diffusion-model-based data augmentation method with reinforcement learning, designed for time-series forecasting with small-scale data. In DAD4TS, a data generator is simultaneously trained with a time-series model and controlled by a reinforcement learning model to efficiently generate samples that improve the forecast accuracy of the time-series model. To support small-scale data, we use mathematical methods instead of conventional VAE methods to train the diffusion model by projecting the time-series data into the geometric space. We validated the effectiveness of DAD4TS with seven comparative methods through qualitative and quantitative experiments on six real-world datasets and eight time-series models. As a result, DAD4TS was validated on five datasets.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 32 of its 52 references that are in the map. First posted on arXiv 18 May 2026.

Builds on

32 of 52 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Diffusion-TS: Interpretable Diffusion for General Time Series Generation4 Mar
  2. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow7 Sep

Other references · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2022Classifier-Free Diffusion Guidancecited by 5,717
  5. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  6. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  7. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  8. 2024Chronos: Learning the Language of Time Seriescited by 712
  9. 2020What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimationcited by 492
  10. 2020Time Series Data Augmentation for Deep Learning: A Surveycited by 225
  11. 2018Adversarial Audio Synthesiscited by 222
  12. 2021TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generationcited by 139
18 more
  1. 2019Data Valuation using Reinforcement Learningcited by 115
  2. 2025TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learningcited by 107
  3. 2020COT-GAN: Generating Sequential Data via Causal Optimal Transportcited by 70
  4. 2023LAVA: Data Valuation without Pre-Specified Learning Algorithmscited by 69
  5. 2023OpenDataVal: a Unified Benchmark for Data Valuationcited by 55
  6. 2025OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domaincited by 25
  7. 2023SaDI: A Self-adaptive Decomposed Interpretable Framework for Electric Load Forecasting under Extreme Eventscited by 21
  8. 2024Data Readiness for AI: A 360-Degree Surveycited by 15
  9. 2025Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approachcited by 14
  10. 2023Data Augmentation for Seizure Prediction with Generative Diffusion Modelcited by 13
  11. 2021Deep Time Series Models for Scarce Datacited by 8
  12. 2025TarDiff: Target-Oriented Diffusion Guidance for Synthetic Electronic Health Record Time Series Generationcited by 8
  13. 2026TempusBench: An Evaluation Framework for Time-Series Forecastingcited by 4
  14. 2024ReAugment: Model Zoo-Guided RL for Few-Shot Time Series Augmentation and Forecastingcited by 3
  15. 2025AugGen: Synthetic Augmentation using Diffusion Models Can Improve Recognitioncited by 3
  16. 2026OATS: Online Data Augmentation for Time Series Foundation Modelscited by 3
  17. 2025A Time-Series Data Augmentation Model through Diffusion and Transformer Integrationcited by 1
  18. 2025Data Augmentation in Time Series Forecasting through Inverted Frameworkcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024The Rise of Diffusion Models in Time-Series Forecasting
  2. 2023Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting
  3. 2025DS-Diffusion: Data Style-Guided Diffusion Model for Time-Series Generation
  4. 2023Diffusion Models for Time Series Applications: A Survey
  5. 2024Retrieval-Augmented Diffusion Models for Time Series Forecasting
  6. 2024ANT: Adaptive Noise Schedule for Time Series Diffusion Models
  7. 2025Diffusion Models for Time Series Forecasting: A Survey
  8. 2025Time Series Forecasting via Reasoning: A Slow-Thinking Approach with Reinforcement Fine-Tuned LLMs