mlsanityData to 7 Oct 2026

TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting

arXiv 2405.14616 ↗First posted 23 May 2024cs.LG cs.AIcited by 333

Not on the map. Why?

Abstract (arXiv)

Time series forecasting is widely used in extensive applications, such as traffic planning and weather forecasting. However, real-world time series usually present intricate temporal variations, making forecasting extremely challenging. Going beyond the mainstream paradigms of plain decomposition and multiperiodicity analysis, we analyze temporal variations in a novel view of multiscale-mixing, which is based on an intuitive but important observation that time series present distinct patterns in different sampling scales. The microscopic and the macroscopic information are reflected in fine and coarse scales respectively, and thereby complex variations can be inherently disentangled. Based on this observation, we propose TimeMixer as a fully MLP-based architecture with Past-Decomposable-Mixing (PDM) and Future-Multipredictor-Mixing (FMM) blocks to take full advantage of disentangled multiscale series in both past extraction and future prediction phases. Concretely, PDM applies the decomposition to multiscale series and further mixes the decomposed seasonal and trend components in fine-to-coarse and coarse-to-fine directions separately, which successively aggregates the microscopic seasonal and macroscopic trend information. FMM further ensembles multiple predictors to utilize complementary forecasting capabilities in multiscale observations. Consequently, TimeMixer is able to achieve consistent state-of-the-art performances in both long-term and short-term forecasting tasks with favorable run-time efficiency.

Key facts. Cited by 333 papers in the map (data through 7 Oct 2026). Builds on 21 of its 40 references that are in the map. First posted on arXiv 23 May 2024.

Builds on

21 of 40 references.

References · 21

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  4. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  5. 2020Reformer: The Efficient Transformercited by 1,658
  6. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  7. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  8. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  9. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  10. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  11. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  12. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 744
9 more
  1. 2021FNet: Mixing Tokens with Fourier Transformscited by 343
  2. 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 335
  3. 2017A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Predictioncited by 245
  4. 2023TSMixer: An All-MLP Architecture for Time Series Forecastingcited by 232
  5. 2022Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structurescited by 158
  6. 2022FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecastingcited by 147
  7. 2022N-HiTS: Neural Hierarchical Interpolation for Time Series Forecastingcited by 146
  8. 2022Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecastingcited by 54
  9. 2023MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixingcited by 52

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 48; 2025: 151; 2026: 134.

333 papers.

Sort:

By area:

  1. 2024Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Expertscited by 280
  2. 2024Deep Time Series Models: A Comprehensive Survey and Benchmarkcited by 191
  3. 2024TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysiscited by 113
  4. 2024CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patternscited by 102
  5. 2024Kolmogorov-Arnold Networks for Time Series: Bridging Predictive Power and Interpretabilitycited by 69
  6. 2024Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysiscited by 65
  7. 2025A Comprehensive Survey of Deep Learning for Multivariate Time Series Forecasting: A Channel Strategy Perspectivecited by 58
  8. 2025DBLoss: Decomposition-based Loss Function for Time Series Forecastingcited by 44
  9. 2025TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loopcited by 39
  10. 2024TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecastingcited by 38
  11. 2025Time Series Forecasting via Reasoning: A Slow-Thinking Approach with Reinforcement Fine-Tuned LLMscited by 34
  12. 2025Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspectivecited by 34
38 more
  1. 2025LightGTS: A Lightweight General Time Series Forecasting Modelcited by 28
  2. 2025TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecastingcited by 27
  3. 2025OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domaincited by 25
  4. 2025Time-o1: Time-Series Forecasting Needs Transformed Label Alignmentcited by 22
  5. 2024Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecastingcited by 21
  6. 2025Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecastingcited by 19
  7. 2024Are Self-Attentions Effective for Time Series Forecasting?cited by 18
  8. 2024xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memoriescited by 18
  9. 2025FreEformer: Frequency Enhanced Transformer for Multivariate Time Series Forecastingcited by 18
  10. 2025TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-statecited by 16
  11. 2025Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Seriescited by 16
  12. 2025From Values to Tokens: An LLM-Driven Framework for Context-aware Time Series Forecasting via Symbolic Discretizationcited by 13
  13. 2025SciTS: Scientific Time Series Understanding and Generation with LLMscited by 13
  14. 2025DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignmentcited by 13
  15. 2025CrossAD: Time Series Anomaly Detection with Cross-scale Associations and Cross-window Modelingcited by 12
  16. 2025TSPulse: Tiny Pre-Trained Models with Disentangled Representations for Rapid Time-Series Analysiscited by 11
  17. 2025TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecastingcited by 11
  18. 2024Fourier Head: Helping Large Language Models Learn Complex Probability Distributionscited by 10
  19. 2025Multimodal Large Models Are Effective Action Anticipatorscited by 10
  20. 2025Time Series Analysis in Frequency Domain: A Survey of Open Challenges, Opportunities and Benchmarkscited by 10
  21. 2025FeDaL: Federated Dataset Learning for General Time Series Foundation Modelscited by 10
  22. 2025Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Modelscited by 10
  23. 2025Glocal Information Bottleneck for Time Series Imputationcited by 9
  24. 2026The Forecast After the Forecast: A Post-Processing Shift in Time Seriescited by 9
  25. 2024CMamba: Channel Correlation Enhanced State Space Models for Multivariate Time Series Forecastingcited by 8
  26. 2025Kairos: Toward Adaptive and Parameter-Efficient Time Series Foundation Modelscited by 8
  27. 2025Selective Learning for Deep Time Series Forecastingcited by 8
  28. 2025AutoHFormer: Efficient Hierarchical Autoregressive Transformer for Time Series Predictioncited by 7
  29. 2025PhaseFormer: From Patches to Phases for Efficient and Effective Time Series Forecastingcited by 7
  30. 2024DeformTime: Capturing Variable Dependencies with Deformable Attention for Time Series Forecastingcited by 6
  31. 2024Are KANs Effective for Multivariate Time Series Forecasting?cited by 6
  32. 2024A Survey of Financial AI: Architectures, Advances and Open Challengescited by 6
  33. 2025Learning General Causal Structures with Hidden Dynamic Process for Climate Analysiscited by 6
  34. 2025TimeRecipe: A Time-Series Forecasting Recipe via Benchmarking Module Level Effectivenesscited by 6
  35. 2025SEMPO: Lightweight Foundation Models for Time Series Forecastingcited by 6
  36. 2024Benchmarking Physics-Informed Time-Series Models for Operational Global Station Weather Forecastingcited by 5
  37. 2024Metadata Matters for Time Series: Informative Forecasting with Transformerscited by 5
  38. 2024Peri-midFormer: Periodic Pyramid Transformer for Time Series Analysiscited by 5

50 most cited of 333 All 333 (JSON)