mlsanityData to 7 Oct 2026

Deep Time-Series Forecasting in 10 Years: A Survey

arXiv 2603.19899 ↗First posted 20 Mar 2026stat.ML cs.LG stat.APcited by 0

Not on the map. Why?

Abstract (arXiv)

Autocorrelation is a common property of time-series, where each observation is dependent on its predecessors. In deep time-series forecasting, it raises two central challenges: (1) designing backbone architectures to model autocorrelation in history sequences, and (2) devising loss functions to model autocorrelation in label sequences. Recent studies have made strides in tackling these challenges, but a systematic survey examining both aspects remains lacking. To bridge this gap, this paper reviews deep time-series forecasting from an autocorrelation modeling perspective, offering two contributions beyond existing surveys. First, it introduces a taxonomy that jointly covers both backbone architectures and loss functions, whereas prior surveys provide limited coverage of the latter. Second, it analyzes the motivations and insights underlying the surveyed literature from a unified autocorrelation perspective, providing a holistic overview of the field's evolution. Additional resources and details are available at https://github.com/Master-PLC/Awesome-TSF-Papers.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 162 of its 254 references that are in the map. First posted on arXiv 20 Mar 2026.

Builds on

162 of 254 references.

References · 162

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  5. 2022Scalable Diffusion Models with Transformerscited by 5,931
  6. 2022Generative Adversarial Networkscited by 5,603
  7. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  8. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,424
  9. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  10. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  11. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  12. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
38 more
  1. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  2. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  3. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  4. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  5. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  6. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  7. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 906
  8. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  9. 2023RWKV: Reinventing RNNs for the Transformer Eracited by 814
  10. 2024Chronos: Learning the Language of Time Seriescited by 712
  11. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 680
  12. 2023A decoder-only foundation model for time-series forecastingcited by 650
  13. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 615
  14. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 606
  15. 2020HiPPO: Recurrent Memory with Optimal Polynomial Projectionscited by 600
  16. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 588
  17. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 577
  18. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 548
  19. 2023Large Language Models Are Zero-Shot Time Series Forecasterscited by 491
  20. 2022Transformers in Time Series: A Surveycited by 489
  21. 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 453
  22. 2023Resurrecting Recurrent Neural Networks for Long Sequencescited by 397
  23. 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 335
  24. 2024TimeMixer: Decomposable Multiscale Mixing for Time Series Forecastingcited by 333
  25. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecastingcited by 332
  26. 2023Long-term Forecasting with TiDE: Time-series Dense Encodercited by 327
  27. 2024Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Expertscited by 280
  28. 2017Soft-DTW: a Differentiable Loss Function for Time-Seriescited by 265
  29. 2024TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methodscited by 242
  30. 2024TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variablescited by 241
  31. 2024Foundation Models for Time Series Analysis: A Tutorial and Surveycited by 234
  32. 2023TSMixer: An All-MLP Architecture for Time Series Forecastingcited by 232
  33. 2020Time Series Data Augmentation for Deep Learning: A Surveycited by 225
  34. 2018Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noisecited by 216
  35. 2024Timer: Generative Pre-trained Transformers Are Large Time Series Modelscited by 198
  36. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 195
  37. 2024Deep Time Series Models: A Comprehensive Survey and Benchmarkcited by 191
  38. 2023FITS: Modeling Time Series with 10k Parameterscited by 185

50 most cited of 162 All 162 (JSON)

Built on by

Not cited yet.