mlsanityData to 7 Oct 2026

MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing

arXiv 2302.04501 ↗First posted 9 Feb 2023cs.LG cs.AIcited by 52

Not on the map. Why?

Abstract (arXiv)

Multivariate time series forecasting has been widely used in various practical scenarios. Recently, Transformer-based models have shown significant potential in forecasting tasks due to the capture of long-range dependencies. However, recent studies in the vision and NLP fields show that the role of attention modules is not clear, which can be replaced by other token aggregation operations. This paper investigates the contributions and deficiencies of attention mechanisms on the performance of time series forecasting. Specifically, we find that (1) attention is not necessary for capturing temporal dependencies, (2) the entanglement and redundancy in the capture of temporal and channel interaction affect the forecasting performance, and (3) it is important to model the mapping between the input and the prediction sequence. To this end, we propose MTS-Mixers, which use two factorized modules to capture temporal and channel dependencies. Experimental results on several real-world datasets show that MTS-Mixers outperform existing Transformer-based models with higher efficiency.

Key facts. Cited by 52 papers in the map (data through 7 Oct 2026). Builds on 26 of its 43 references that are in the map. First posted on arXiv 9 Feb 2023.

Builds on

26 of 43 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  5. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  6. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  7. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  8. 2019Generating Long Sequences with Sparse Transformerscited by 1,523
  9. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  10. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  11. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  12. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
14 more
  1. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  2. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  3. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 744
  4. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 606
  5. 2021FNet: Mixing Tokens with Fourier Transformscited by 343
  6. 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 335
  7. 2020Synthesizer: Rethinking Self-Attention in Transformer Modelscited by 204
  8. 2022N-HiTS: Neural Hierarchical Interpolation for Time Series Forecastingcited by 146
  9. 2022ETSformer: Exponential Smoothing Transformers for Time-series Forecastingcited by 146
  10. 2017Attend and Diagnose: Clinical Time Series Analysis using Attention Modelscited by 105
  11. 2021Is Attention Better Than Matrix Decomposition?cited by 75
  12. 2021Reflash Dropout in Image Super-Resolutioncited by 41
  13. 2022MetaFormer: A Unified Meta Framework for Fine-Grained Recognitioncited by 28
  14. 2019CDSA: Cross-Dimensional Self-Attention for Multivariate, Geo-tagged Time Series Imputationcited by 24

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 14; 2024: 20; 2025: 16; 2026: 2.

52 papers.

Sort:

By area:

  1. 2024TimeMixer: Decomposable Multiscale Mixing for Time Series Forecastingcited by 333
  2. 2024TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysiscited by 113
  3. 2024CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patternscited by 102
  4. 2023CARD: Channel Aligned Robust Blend Transformer for Time Series Forecastingcited by 55
  5. 2023SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecastingcited by 53
  6. 2024From Similarity to Superiority: Channel Clustering for Time Series Forecastingcited by 37
  7. 2024Adaptive Multi-Scale Decomposition Framework for Time Series Forecastingcited by 34
  8. 2024A Survey of Deep Learning and Foundation Models for Time Series Forecastingcited by 32
  9. 2024Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicatorscited by 32
  10. 2025Temporal Query Network for Efficient Multivariate Time Series Forecastingcited by 29
  11. 2023PETformer: Long-term Time Series Forecasting via Placeholder-enhanced Transformercited by 22
  12. 2024RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Taskscited by 22
38 more
  1. 2023MotionTrack: Learning Motion Predictor for Multiple Object Trackingcited by 20
  2. 2023PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecastingcited by 20
  3. 2023MultiSPANS: A Multi-range Spatial-Temporal Transformer Network for Traffic Forecast via Structural Entropy Optimizationcited by 13
  4. 2024TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learningcited by 12
  5. 2023Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mappingcited by 11
  6. 2023SageFormer: Series-Aware Framework for Long-term Multivariate Time Series Forecastingcited by 10
  7. 2025MPTSNet: Integrating Multiscale Periodic Local Patterns and Global Dependencies for Multivariate Time Series Classificationcited by 10
  8. 2024A Mamba Foundation Model for Time Series Forecastingcited by 9
  9. 2025TVNet: A Novel Time Series Analysis Method Based on Dynamic Convolution and 3D-Variationcited by 8
  10. 2024On the Integration of Spatial-Temporal Knowledge: A Lightweight Approach to Atmospheric Time Series Forecastingcited by 7
  11. 2023A Joint Time-frequency Domain Transformer for Multivariate Time Series Forecastingcited by 5
  12. 2024LiNo: Advancing Recursive Residual Decomposition of Linear and Nonlinear Patterns for Robust Time Series Forecastingcited by 3
  13. 2025TFKAN: Time-Frequency KAN for Long-Term Time Series Forecastingcited by 3
  14. 2026MambaSL: Exploring Single-Layer Mamba for Time Series Classificationcited by 3
  15. 2024Distillation Enhanced Time Series Forecasting Network with Momentum Contrastive Learningcited by 2
  16. 2023Two-Stage Aggregation with Dynamic Local Attention for Irregular Time Seriescited by 1
  17. 2024TiVaT: A Transformer with a Single Unified Mechanism for Capturing Asynchronous Dependencies in Multivariate Time Series Forecastingcited by 1
  18. 2024EffiCANet: Efficient Time Series Forecasting with Convolutional Attentioncited by 1
  19. 2024MTS-UNMixers: Multivariate Time Series Forecasting via Channel-Time Dual Unmixingcited by 1
  20. 2024Revisiting PCA for time series reduction in temporal dimensioncited by 1
  21. 2025MFRS: A Multi-Frequency Reference Series Approach to Scalable and Accurate Time-Series Forecastingcited by 1
  22. 2025ARIES: Relation Assessment and Model Recommendation for Deep Time Series Forecastingcited by 1
  23. 2025Hydra: Dual Exponentiated Memory for Multivariate Time Series Analysiscited by 1
  24. 2023Minimalist Traffic Prediction: Linear Layer Is All You Needcited by 0
  25. 2023A Simple Framework for Multi-mode Spatial-Temporal Data Modelingcited by 0
  26. 2023Leveraging Herpangina Data to Enhance Hospital-level Prediction of Hand-Foot-and-Mouth Disease Admissions Using UPTSTcited by 0
  27. 2023Multichannel consecutive data cross-extraction with 1DCNN-attention for diagnosis of power transformercited by 0
  28. 2024Mixer is more than just a modelcited by 0
  29. 2024ISMRNN: An Implicitly Segmented RNN Method with Mamba for Long-Term Time Series Forecastingcited by 0
  30. 2024A Wave is Worth 100 Words: Investigating Cross-Domain Transferability in Time Seriescited by 0
  31. 2025Energy-Aware Pattern Disentanglement: A Generalizable Pattern Assisted Architecture for Multi-task Time Series Analysiscited by 0
  32. 2025Logo-LLM: Local and Global Modeling with Large Language Models for Time Series Forecastingcited by 0
  33. 2025MS-DFTVNet:A Long-Term Time Series Prediction Method Based on Multi-Scale Deformable Convolutioncited by 0
  34. 2025FAF: A Feature-Adaptive Framework for Few-Shot Time Series Forecastingcited by 0
  35. 2025CATS-Linear: Classification Auxiliary Linear Model for Time Series Forecastingcited by 0
  36. 2025Neural Architecture Search for global multi-step Forecasting of Energy Production Time Seriescited by 0
  37. 2025TTF: A Trapezoidal Temporal Fusion Framework for LTV Forecasting in Douyincited by 0
  38. 2025PeriodNet: Boosting the Potential of Attention Mechanism for Time Series Forecastingcited by 0

50 most cited of 52 All 52 (JSON)