mlsanityData to 14 Oct 2026

ms-Mamba: Multi-scale Mamba for Time-Series Forecasting

arXiv 2504.07654 ↗First posted 10 Apr 2025cs.LG cs.AIcited by 8

On the map: State-space sequence models (S4, Mamba) → Time series forecasting with SSMs

Abstract (arXiv)

The problem of Time-series Forecasting is generally addressed by recurrent, Transformer-based and the recently proposed Mamba-based architectures. However, existing architectures generally process their input at a single temporal scale, which may be sub-optimal for many tasks where information changes over multiple time scales. In this paper, we introduce a novel architecture called Multi-scale Mamba (ms-Mamba) to address this gap. ms-Mamba incorporates multiple temporal scales by using multiple Mamba blocks with different sampling rates (Deltas). Our experiments on many benchmarks demonstrate that ms-Mamba outperforms state-of-the-art approaches, including the recently proposed Transformer-based and Mamba-based models. For example, on the Solar-Energy dataset, ms-Mamba outperforms its closest competitor S-Mamba (0.229 vs. 0.240 in terms of mean-squared error) while using fewer parameters (3.53M vs. 4.77M), less memory (13.46MB vs. 18.18MB), and less operations (14.93G vs. 20.53G MACs), averaged across four forecast lengths. Codes and models will be made available.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in Time series forecasting with SSMs, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 40 of its 55 references that are in the map. First posted on arXiv 10 Apr 2025.

Builds on

40 of 55 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Is Mamba Effective for Time Series Forecasting?17 Mar

Other references · 39

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  4. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  5. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  6. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  7. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  8. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  9. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  10. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  11. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  12. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,056
27 more
  1. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 931
  2. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  3. 2022Simplified State Space Layers for Sequence Modelingcited by 788
  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. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 608
  7. 2022Hungry Hungry Hippos: Towards Language Modeling with State Space Modelscited by 499
  8. 2022Transformers in Time Series: A Surveycited by 497
  9. 2020Time Series Forecasting With Deep Learning: A Surveycited by 459
  10. 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 338
  11. 2023Long-term Forecasting with TiDE: Time-series Dense Encodercited by 332
  12. 2023TSMixer: An All-MLP Architecture for Time Series Forecastingcited by 240
  13. 2023Frequency-domain MLPs are More Effective Learners in Time Series Forecastingcited by 172
  14. 2022Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structurescited by 160
  15. 2022ETSformer: Exponential Smoothing Transformers for Time-series Forecastingcited by 148
  16. 2020Deep Learning for Time Series Forecasting: Tutorial and Literature Surveycited by 117
  17. 2016Hierarchical Multiscale Recurrent Neural Networkscited by 104
  18. 2024Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecastingcited by 104
  19. 2024MedMamba: Vision Mamba for Medical Image Classificationcited by 88
  20. 2022Transformers in Time-series Analysis: A Tutorialcited by 46
  21. 2023Improving Position Encoding of Transformers for Multivariate Time Series Classificationcited by 45
  22. 2024Is Mamba Capable of In-Context Learning?cited by 45
  23. 2024A Survey of Mambacited by 39
  24. 2024A Survey of Deep Learning and Foundation Models for Time Series Forecastingcited by 33
  25. 2023Multi-scale Transformer Pyramid Networks for Multivariate Time Series Forecastingcited by 9
  26. 2024Multi-Scale Dilated Convolution Network for Long-Term Time Series Forecastingcited by 5
  27. 2022Temporal Saliency Detection Towards Explainable Transformer-based Timeseries Forecastingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 6.

8 papers.

  1. 2026GAMMA-Net: Adaptive Long-Horizon Traffic Spatio-Temporal Forecasting Model based on Interleaved Graph Attention and Multi-Axis Mambacited by 1
  2. 2025ss-Mamba: Semantic-Spline Selective State-Space Modelcited by 0
  3. 2025VFEM: Visual Feature Empowered Multivariate Time Series Forecasting with Cross-Modal Fusioncited by 0
  4. 2026ASGMamba: Adaptive Spectral Gating Mamba for Multivariate Time Series Forecastingcited by 0
  5. 2026Permutation-Equivariant 2D State Space Models: Theory and Canonical Architecture for Multivariate Time Seriescited by 0
  6. 2026PIMSM: Physics-Informed Multi-Scale Mamba for Stable Neural Representations under Distribution Shiftcited by 0
  7. 2026A Unified Backbone--Expert Framework with Relation-Token and Residual--Classifier Interfaces for Automatic Modulation Recognitioncited by 0
  8. 2026MARS: Multi-resolution Adaptive Routing for Sequential Recommendationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024SST: Multi-Scale Hybrid Mamba-Transformer Experts for Time Series Forecasting
  2. 2025DC-Mamber: A Dual Channel Prediction Model based on Mamba and Linear Transformer for Multivariate Time Series Forecasting
  3. 2024Integration of Mamba and Transformer -- MAT for Long-Short Range Time Series Forecasting with Application to Weather Dynamics
  4. 2024FMamba: Mamba based on Fast-attention for Multivariate Time-series Forecasting
  5. 2024TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecasting
  6. 2024A Mamba Foundation Model for Time Series Forecasting
  7. 2024Bi-Mamba+: Bidirectional Mamba for Time Series Forecasting
  8. 2026DMamba: Decomposition-enhanced Mamba for Time Series Forecasting