mlsanityData to 14 Oct 2026

Tailored Forecasting from Short Time Series via Meta-learning

arXiv 2501.16325 ↗First posted 27 Jan 2025cs.LG nlin.CD physics.comp-phcited by 2

Not on the map. Why?

Abstract (arXiv)

Machine learning models can effectively forecast dynamical systems from time-series data, but they typically require large amounts of past data, making forecasting particularly challenging for systems with limited history. To overcome this, we introduce Meta-learning for Tailored Forecasting using Related Time Series (METAFORS), which generalizes knowledge across systems to enable forecasting in data-limited scenarios. By learning from a library of models trained on longer time series from potentially related systems, METAFORS builds and initializes a model tailored to short time-series data from the system of interest. Using a reservoir computing implementation and testing on simulated chaotic systems, we demonstrate that METAFORS can reliably predict both short-term dynamics and long-term statistics without requiring contextual labels. We see this even when test and related systems exhibit substantially different behaviors, highlighting METAFORS' strengths in data-limited scenarios.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 33 of its 89 references that are in the map. First posted on arXiv 27 Jan 2025.

Builds on

33 of 89 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  4. 2017A Survey on Multi-Task Learningcited by 840
  5. 2024Chronos: Learning the Language of Time Seriescited by 759
  6. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  7. 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
  8. 2019Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019cited by 273
  9. 2021Next Generation Reservoir Computingcited by 160
  10. 2020Meta-learning framework with applications to zero-shot time-series forecastingcited by 70
  11. 2019Hierarchically Structured Meta-learningcited by 68
  12. 2018Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Modelcited by 57
21 more
  1. 2020Machine learning prediction of critical transition and system collapsecited by 54
  2. 2022Generalizing to New Physical Systems via Context-Informed Dynamics Modelcited by 50
  3. 2021LEADS: Learning Dynamical Systems that Generalize Across Environmentscited by 40
  4. 2021Meta-Learning Dynamics Forecasting Using Task Inferencecited by 38
  5. 2024Out-of-Domain Generalization in Dynamical Systems Reconstructioncited by 33
  6. 2022A Systematic Exploration of Reservoir Computing for Forecasting Complex Spatiotemporal Dynamicscited by 30
  7. 2024Zero-shot forecasting of chaotic systemscited by 28
  8. 2020Bridging Physics-based and Data-driven modeling for Learning Dynamical Systemscited by 25
  9. 2020Combining Machine Learning with Knowledge-Based Modeling for Scalable Forecasting and Subgrid-Scale Closure of Large, Complex, Spatiotemporal Systemscited by 23
  10. 2021Parallel Machine Learning for Forecasting the Dynamics of Complex Networkscited by 17
  11. 2019Separation of Chaotic Signals by Reservoir Computingcited by 12
  12. 2022Catch-22s of reservoir computingcited by 11
  13. 2023Extrapolating tipping points and simulating non-stationary dynamics of complex systems using efficient machine learningcited by 9
  14. 2018Meta-learning autoencoders for few-shot predictioncited by 7
  15. 2021Initializing LSTM internal states via manifold learningcited by 7
  16. 2020Panda: Partitioned Data Security on Outsourced Sensitive and Non-sensitive Datacited by 5
  17. 2021Forecasting Brain Activity Based on Models of Spatio-Temporal Brain Dynamics: A Comparison of Graph Neural Network Architecturescited by 4
  18. 2022Comparing trained and untrained probabilistic ensemble forecasts of COVID-19 cases and deaths in the United Statescited by 4
  19. 2025Unsupervised learning for anticipating critical transitionscited by 4
  20. 2024Learning to learn ecosystems from limited data -- a meta-learning approachcited by 2
  21. 2021A Meta-learning Approach to Reservoir Computing: Time Series Prediction with Limited Datacited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecastingcited by 2
  2. 2026Position: The Inevitable End of One-Architecture-Fits-All-Domains in Time Series Forecastingcited by 2