mlsanityData to 7 Oct 2026

Out-of-Distribution Generalization in Time Series: A Survey

arXiv 2503.13868 ↗First posted 18 Mar 2025cs.LG cs.AIcited by 15

Not on the map. Why?

Abstract (arXiv)

Time series frequently manifest distribution shifts, diverse latent features, and non-stationary learning dynamics, particularly in open and evolving environments. These characteristics pose significant challenges for out-of-distribution (OOD) generalization. While substantial progress has been made, a systematic synthesis of advancements remains lacking. To address this gap, we present the first comprehensive review of OOD generalization methodologies for time series, organized to delineate the field's evolutionary trajectory and contemporary research landscape. We organize our analysis across three foundational dimensions: data distribution, representation learning, and OOD evaluation. For each dimension, we present several popular algorithms in detail. Furthermore, we highlight key application scenarios, emphasizing their real-world impact. Finally, we identify persistent challenges and propose future research directions. A detailed summary of the methods reviewed for the generalization of OOD in time series can be accessed at https://tsood-generalization.com.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 119 of its 252 references that are in the map. First posted on arXiv 18 Mar 2025.

Builds on

119 of 252 references.

References · 119

  1. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  2. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  3. 2023A Survey on Multimodal Large Language Modelscited by 898
  4. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  5. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  6. 2024Chronos: Learning the Language of Time Seriescited by 712
  7. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 680
  8. 2023A decoder-only foundation model for time-series forecastingcited by 650
  9. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 615
  10. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 588
  11. 2023Large Language Models Are Zero-Shot Time Series Forecasterscited by 491
  12. 2022Transformers in Time Series: A Surveycited by 489
38 more
  1. 2020Learning under Concept Drift: A Reviewcited by 470
  2. 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 453
  3. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  4. 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 403
  5. 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 335
  6. 2018Stronger generalization bounds for deep nets via a compression approachcited by 306
  7. 2021Unsolved Problems in ML Safetycited by 291
  8. 2020The Risks of Invariant Risk Minimizationcited by 262
  9. 2020Transfer Learning in Deep Reinforcement Learning: A Surveycited by 259
  10. 2024Timer: Generative Pre-trained Transformers Are Large Time Series Modelscited by 198
  11. 2020A review on outlier/anomaly detection in time series datacited by 187
  12. 2024Are Language Models Actually Useful for Time Series Forecasting?cited by 163
  13. 2023TimeGPT-1cited by 149
  14. 2023TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecastingcited by 136
  15. 2018Rademacher Complexity for Adversarially Robust Generalizationcited by 132
  16. 2022Conformal Inference for Online Prediction with Arbitrary Distribution Shiftscited by 123
  17. 2024Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Seriescited by 120
  18. 2024CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuningcited by 105
  19. 2020Benchmarking Deep Learning Interpretability in Time Series Predictionscited by 102
  20. 2023ForecastPFN: Synthetically-Trained Zero-Shot Forecastingcited by 102
  21. 2022Out-Of-Distribution Generalization on Graphs: A Surveycited by 97
  22. 2024UniTS: A Unified Multi-Task Time Series Modelcited by 93
  23. 2024ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Datacited by 92
  24. 2023Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series Forecastingcited by 91
  25. 2021Perception and Sensing for Autonomous Vehicles Under Adverse Weather Conditions: A Surveycited by 81
  26. 2024Language Models Still Struggle to Zero-shot Reason about Time Seriescited by 81
  27. 2021OOD-GNN: Out-of-Distribution Generalized Graph Neural Networkcited by 78
  28. 2023OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensemblingcited by 71
  29. 2020Meta-learning framework with applications to zero-shot time-series forecastingcited by 70
  30. 2018Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysiscited by 61
  31. 2023Domain Adaptation for Time Series Under Feature and Label Shiftscited by 60
  32. 2022Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecastingcited by 54
  33. 2020Conformal prediction for time seriescited by 53
  34. 2023MSGNet: Learning Multi-Scale Inter-Series Correlations for Multivariate Time Series Forecastingcited by 50
  35. 2020In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustnesscited by 49
  36. 2024Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilitiescited by 48
  37. 2018RAIM: Recurrent Attentive and Intensive Model of Multimodal Patient Monitoring Datacited by 47
  38. 2024Position: What Can Large Language Models Tell Us about Time Series Analysiscited by 47

50 most cited of 119 All 119 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 10.

15 papers.

Sort:

By area:

  1. 2026TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series Taskscited by 15
  2. 2025Accuracy, Memory Efficiency and Generalization: A Comparative Study on Liquid Neural Networks and Recurrent Neural Networkscited by 3
  3. 2025Temp-SCONE: A Novel Out-of-Distribution Detection and Domain Generalization Framework for Wild Data with Temporal Shiftcited by 3
  4. 2026TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learningcited by 2
  5. 2025A Comparative Study on How Data Normalization Affects Zero-Shot Generalization in Time Series Foundation Modelscited by 1
  6. 2026Assessing the Robustness of Climate Foundation Models under No-Analog Distribution Shiftscited by 1
  7. 2026Outsmarting the Chameleon: Counterfactual Decoupling for Tactical OOD Shifts in Live Streaming Risk Assessmentcited by 1
  8. 2025ERIS: An Energy-Guided Feature Disentanglement Framework for Out-of-Distribution Time Series Classificationcited by 0
  9. 2025General OOD Detection via Model-aware and Subspace-aware Variable Prioritycited by 0
  10. 2026Do Transformers Have the Ability for Periodicity Generalization?cited by 0
  11. 2026Manifold-Aware Temporal Domain Generalization for Large Language Modelscited by 0
  12. 2026Cross-Machine Anomaly Detection Leveraging Pre-trained Time-series Modelcited by 0
3 more
  1. 2026Human-Machine Collaboration on Generative Meta-Learning: Model and Algorithmcited by 0
  2. 2026ALER-TI: Aligned Latent Embedding Retrieval for Time Series Imputationcited by 0
  3. 2026Model-Agnostic Online Certificate-Driven Calibration for Time Series Forecasting Under Distribution Shiftcited by 0