mlsanityData to 14 Oct 2026

DynG-Diff: A State-Aware Dynamic Guidance Diffusion Framework for Probabilistic Time Series Forecasting

arXiv 2609.02068 ↗First posted 2 Sep 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Probabilistic multivariate time series (MTS) forecasting is crucial for modeling complex dynamical systems. However, existing diffusion-based methods rely on task-specific conditional paradigms that lack flexibility and struggle with inherent "information heterogeneity"--the significantly varying noise levels and evolutionary patterns across variables. To address this, we propose DynG-Diff, a variable-sensitive dynamic guidance diffusion framework for probabilistic multivariate time-series forecasting: (1) DynG-Diff adopts a two-stage separated training strategy and uses an unconditional diffusion backbone to model the joint distribution of multivariate time series. (2) DynG-Diff introduces a lightweight state-aware policy network that adaptively infers variable reliability from real-time noisy states and one-step denoising estimates, outputting a dynamic guidance strength matrix. (3) DynG-Diff mathematically formulates this dynamic weight as the local precision of the observation distribution, enabling precise guidance for high-confidence variables during inference while filtering out interference from anomalous noise. Extensive experiments on real-world benchmarks demonstrate competitive probabilistic forecasting performance against state-of-the-art conditional diffusion models and improved robustness under severe observation corruption.The implementation code is available at: https://github.com/TT-20011031/DynG-Diff

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 38 references that are in the map. First posted on arXiv 2 Sep 2026.

Builds on

29 of 38 references.

References · 29

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  4. 2022Classifier-Free Diffusion Guidancecited by 5,847
  5. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  6. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  7. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  8. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  9. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
  10. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 931
  11. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 927
  12. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
17 more
  1. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecastingcited by 337
  2. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 333
  3. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 198
  4. 2024Diffusion-TS: Interpretable Diffusion for General Time Series Generationcited by 184
  5. 2019High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processescited by 148
  6. 2020Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flowscited by 144
  7. 2021TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generationcited by 142
  8. 2016C-RNN-GAN: Continuous recurrent neural networks with adversarial trainingcited by 132
  9. 2023Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglementcited by 90
  10. 2023Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecastingcited by 88
  11. 2021PSA-GAN: Progressive Self Attention GANs for Synthetic Time Seriescited by 58
  12. 2023On the Constrained Time-Series Generation Problemcited by 54
  13. 2025Feedback Guidance of Diffusion Modelscited by 16
  14. 2024DiffsFormer: A Diffusion Transformer on Stock Factor Augmentationcited by 9
  15. 2023Hybrid Variational Autoencoder for Time Series Forecastingcited by 8
  16. 2025RDIT: Residual-based Diffusion Implicit Models for Probabilistic Time Series Forecastingcited by 4
  17. 2024Channel-aware Contrastive Conditional Diffusion for Multivariate Probabilistic Time Series Forecastingcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Differencing the Diffusion Trajectory toward Uncertain Components for Time Series Forecasting
  2. 2026DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting
  3. 2025Non-stationary Diffusion For Probabilistic Time Series Forecasting
  4. 2025Effective Probabilistic Time Series Forecasting with Fourier Adaptive Noise-Separated Diffusion
  5. 2026GARDiff: Graph-Aligned Residual Diffusion for Probabilistic Multivariate Time-Series Forecasting
  6. 2026Quantile-Guided Diffusion for Probabilistic Time-Series Forecasting
  7. 2025Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics
  8. 2023DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal Forecasting