mlsanityData to 7 Oct 2026

TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis

arXiv 2210.02186 ↗First posted 5 Oct 2022cs.LGcited by 1,030

Not on the map. Why?

Cited by 33 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Time series analysis is of immense importance in extensive applications, such as weather forecasting, anomaly detection, and action recognition. This paper focuses on temporal variation modeling, which is the common key problem of extensive analysis tasks. Previous methods attempt to accomplish this directly from the 1D time series, which is extremely challenging due to the intricate temporal patterns. Based on the observation of multi-periodicity in time series, we ravel out the complex temporal variations into the multiple intraperiod- and interperiod-variations. To tackle the limitations of 1D time series in representation capability, we extend the analysis of temporal variations into the 2D space by transforming the 1D time series into a set of 2D tensors based on multiple periods. This transformation can embed the intraperiod- and interperiod-variations into the columns and rows of the 2D tensors respectively, making the 2D-variations to be easily modeled by 2D kernels. Technically, we propose the TimesNet with TimesBlock as a task-general backbone for time series analysis. TimesBlock can discover the multi-periodicity adaptively and extract the complex temporal variations from transformed 2D tensors by a parameter-efficient inception block. Our proposed TimesNet achieves consistent state-of-the-art in five mainstream time series analysis tasks, including short- and long-term forecasting, imputation, classification, and anomaly detection. Code is available at this repository: https://github.com/thuml/TimesNet.

Key facts. Cited by 1,030 papers in the map (data through 7 Oct 2026). Builds on 32 of its 52 references that are in the map. First posted on arXiv 5 Oct 2022.

Builds on

32 of 52 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2020Language Models are Few-Shot Learnerscited by 32,199
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  6. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  7. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  8. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  9. 2014Going Deeper with Convolutionscited by 4,231
  10. 2022A ConvNet for the 2020scited by 3,545
  11. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  12. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,424
20 more
  1. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  2. 2019Similarity of Neural Network Representations Revisitedcited by 1,695
  3. 2020Reformer: The Efficient Transformercited by 1,658
  4. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  5. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  6. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  7. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  8. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 744
  9. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 606
  10. 2020Time Series Forecasting With Deep Learning: A Surveycited by 457
  11. 2020A Transformer-based Framework for Multivariate Time Series Representation Learningcited by 449
  12. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 407
  13. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 387
  14. 2019ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernelscited by 336
  15. 2018The UEA multivariate time series classification archive, 2018cited by 330
  16. 2019Unsupervised Scalable Representation Learning for Multivariate Time Seriescited by 267
  17. 2022Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structurescited by 158
  18. 2022N-HiTS: Neural Hierarchical Interpolation for Time Series Forecastingcited by 146
  19. 2022ETSformer: Exponential Smoothing Transformers for Time-series Forecastingcited by 146
  20. 2022Flowformer: Linearizing Transformers with Conservation Flowscited by 69

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 68; 2024: 255; 2025: 368; 2026: 338.

1,030 papers.

Sort:

By area:

  1. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 906
  2. 2024Chronos: Learning the Language of Time Seriescited by 712
  3. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 680
  4. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 615
  5. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 588
  6. 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 453
  7. 2024TimeMixer: Decomposable Multiscale Mixing for Time Series Forecastingcited by 333
  8. 2024Titans: Learning to Memorize at Test Timecited by 303
  9. 2024Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Expertscited by 280
  10. 2024TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variablescited by 241
  11. 2024Timer: Generative Pre-trained Transformers Are Large Time Series Modelscited by 198
  12. 2024Deep Time Series Models: A Comprehensive Survey and Benchmarkcited by 191
38 more
  1. 2023FITS: Modeling Time Series with 10k Parameterscited by 185
  2. 2023TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecastingcited by 170
  3. 2025Sundial: A Family of Highly Capable Time Series Foundation Modelscited by 168
  4. 2023TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Seriescited by 165
  5. 2024Are Language Models Actually Useful for Time Series Forecasting?cited by 163
  6. 2023TimeGPT-1cited by 149
  7. 2023UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecastingcited by 139
  8. 2023Meta-Transformer: A Unified Framework for Multimodal Learningcited by 136
  9. 2024Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Seriescited by 120
  10. 2023Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysiscited by 113
  11. 2024TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysiscited by 113
  12. 2023Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictorscited by 110
  13. 2024CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuningcited by 105
  14. 2024SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameterscited by 103
  15. 2024Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecastingcited by 102
  16. 2024CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patternscited by 102
  17. 2023Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospectscited by 97
  18. 2024UniTS: A Unified Multi-Task Time Series Modelcited by 93
  19. 2024From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflectioncited by 93
  20. 2024CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patchingcited by 91
  21. 2024Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Expertscited by 88
  22. 2024VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasterscited by 87
  23. 2024Timer-XL: Long-Context Transformers for Unified Time Series Forecastingcited by 83
  24. 2024SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time seriescited by 81
  25. 2024FreDF: Learning to Forecast in the Frequency Domaincited by 77
  26. 2024SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusioncited by 75
  27. 2024TSLANet: Rethinking Transformers for Time Series Representation Learningcited by 71
  28. 2024Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysiscited by 65
  29. 2024AutoTimes: Autoregressive Time Series Forecasters via Large Language Modelscited by 63
  30. 2024TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecastingcited by 63
  31. 2024Empowering Time Series Analysis with Large Language Models: A Surveycited by 60
  32. 2025Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecastingcited by 59
  33. 2025A Comprehensive Survey of Deep Learning for Multivariate Time Series Forecasting: A Channel Strategy Perspectivecited by 58
  34. 2024Deep Learning for Multivariate Time Series Imputation: A Surveycited by 57
  35. 2024Scaling Wearable Foundation Modelscited by 57
  36. 2025This Time is Different: An Observability Perspective on Time Series Foundation Modelscited by 57
  37. 2023CARD: Channel Aligned Robust Blend Transformer for Time Series Forecastingcited by 55
  38. 2025Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baselinecited by 54

50 most cited of 1,030 All 1,030 (JSON)