mlsanityData to 7 Oct 2026

Meta-Learning for Physically-Constrained Neural System Identification

arXiv 2501.06167 ↗First posted 10 Jan 2025cs.LG cs.SY eess.SYcited by 5

Not on the map. Why?

Abstract (arXiv)

We present a gradient-based meta-learning framework for rapid adaptation of neural state-space models (NSSMs) for black-box system identification. When applicable, we also incorporate domain-specific physical constraints to improve the accuracy of the NSSM. The major benefit of our approach is that instead of relying solely on data from a single target system, our framework utilizes data from a diverse set of source systems, enabling learning from limited target data, as well as with few online training iterations. Through benchmark examples, we demonstrate the potential of our approach, study the effect of fine-tuning subnetworks rather than full fine-tuning, and report real-world case studies to illustrate the practical application and generalizability of the approach to practical problems with physical-constraints. Specifically, we show that the meta-learned models result in improved downstream performance in model-based state estimation in indoor localization and energy systems.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 34 of its 69 references that are in the map. First posted on arXiv 10 Jan 2025.

Builds on

34 of 69 references.

References · 34

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  4. 2016Matching Networks for One Shot Learningcited by 2,246
  5. 2014How transferable are features in deep neural networks?cited by 1,216
  6. 2019Meta-Learning with Implicit Gradientscited by 523
  7. 2017Deep learning for universal linear embeddings of nonlinear dynamicscited by 491
  8. 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
  9. 2018How to train your MAMLcited by 306
  10. 2017Meta Networkscited by 268
  11. 2017Searching for Activation Functionscited by 158
  12. 2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
22 more
  1. 2021Generalization Bounds For Meta-Learning: An Information-Theoretic Analysiscited by 45
  2. 2021Adaptive-Control-Oriented Meta-Learning for Nonlinear Systemscited by 38
  3. 2021Constructing Neural Network-Based Models for Simulating Dynamical Systemscited by 29
  4. 2020dynoNet: a neural network architecture for learning dynamical systemscited by 28
  5. 2020Nonlinear state-space identification using deep encoder networkscited by 28
  6. 2020On Correctness of Automatic Differentiation for Non-Differentiable Functionscited by 20
  7. 2019Model structures and fitting criteria for system identification with neural networkscited by 16
  8. 2022Identifying the Dynamics of a System by Leveraging Data from Similar Systemscited by 15
  9. 2023From system models to class models: An in-context learning paradigmcited by 13
  10. 2021Deep Identification of Nonlinear Systems in Koopman Formcited by 11
  11. 2020On the Initialization of Nonlinear LFR Model Identification with the Best Linear Approximationcited by 9
  12. 2020Physics-Informed Neural State Space Models via Learning and Evolutioncited by 9
  13. 2020Meta Learning MPC using Finite-Dimensional Gaussian Process Approximationscited by 8
  14. 2022Learning neural state-space models: do we need a state estimator?cited by 6
  15. 2022Optimizing Closed-Loop Performance with Data from Similar Systems: A Bayesian Meta-Learning Approachcited by 5
  16. 2023Physics-Informed Learning Using Hamiltonian Neural Networks with Output Error Noise Modelscited by 5
  17. 2023On the adaptation of in-context learners for system identificationcited by 5
  18. 2024MPC of Uncertain Nonlinear Systems with Meta-Learning for Fast Adaptation of Neural Predictive Modelscited by 4
  19. 2024Physics-Guided State-Space Model Augmentation Using Weighted Regularized Neural Networkscited by 4
  20. 2024A New First-Order Meta-Learning Algorithm with Convergence Guaranteescited by 4
  21. 2018Constrained State Estimation -- A Reviewcited by 2
  22. 2020Meta-Learning Guarantees for Online Receding Horizon Learning Controlcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025Manifold meta-learning for reduced-complexity neural system identificationcited by 2
  2. 2026Point Cloud Sequence Encoding for Material-conditioned Graph Network Simulatorscited by 0
  3. 2026Meta-Learning for Rapid Adaptation in Reference Tracking of Uncertain Nonlinear Systemscited by 0
  4. 2026Learning Dynamical Systems from Multiple Sparse Datasets: A Hierarchical Bayesian Modeling Approachcited by 0
  5. 2026Variational meta-learning inference for low dimensional neural system identificationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Meta-Learning of Neural State-Space Models Using Data From Similar Systems
  2. 2026Online learning of neural state-space models
  3. 2025Neural Network State-Space Estimators ↗
  4. 2026Physics-Guided Recurrent State-Space Neural Networks for Multi-Step Prediction
  5. 2024Meta-Dynamical State Space Models for Integrative Neural Data Analysis
  6. 2026Model-Free Neural Filtering: A Comparison with Classical Filters in Nonlinear Systems
  7. 2022Learning Reduced Nonlinear State-Space Models: an Output-Error Based Canonical Approach
  8. 2022Neural Ordinary Differential Equations for Nonlinear System Identification