mlsanityData to 7 Oct 2026

MetaPhysiCa: OOD Robustness in Physics-informed Machine Learning

arXiv 2303.03181 ↗First posted 6 Mar 2023cs.LG stat.MLcited by 6

Not on the map. Why?

Abstract (arXiv)

A fundamental challenge in physics-informed machine learning (PIML) is the design of robust PIML methods for out-of-distribution (OOD) forecasting tasks. These OOD tasks require learning-to-learn from observations of the same (ODE) dynamical system with different unknown ODE parameters, and demand accurate forecasts even under out-of-support initial conditions and out-of-support ODE parameters. In this work we propose a solution for such tasks, which we define as a meta-learning procedure for causal structure discovery (including invariant risk minimization). Using three different OOD tasks, we empirically observe that the proposed approach significantly outperforms existing state-of-the-art PIML and deep learning methods.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 42 of its 59 references that are in the map. First posted on arXiv 6 Mar 2023.

Builds on

42 of 59 references.

References · 42

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2018Neural Ordinary Differential Equationscited by 3,733
  3. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  4. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  5. 2019Invariant Risk Minimizationcited by 1,832
  6. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
  7. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  8. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 745
  9. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  10. 2019Hamiltonian Neural Networkscited by 702
  11. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 571
  12. 2017Deep learning for universal linear embeddings of nonlinear dynamicscited by 491
30 more
  1. 2021Machine learning accelerated computational fluid dynamicscited by 461
  2. 2018Bilevel Programming for Hyperparameter Optimization and Meta-Learningcited by 403
  3. 2020Lagrangian Neural Networkscited by 388
  4. 2022Message Passing Neural PDE Solverscited by 368
  5. 2017Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equationscited by 362
  6. 2020Discovering Symbolic Models from Deep Learning with Inductive Biasescited by 335
  7. 2018Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equationscited by 233
  8. 2021Gradient-enhanced physics-informed neural networks for forward and inverse PDE problemscited by 220
  9. 2020How Neural Networks Extrapolate: From Feedforward to Graph Neural Networkscited by 218
  10. 2019Towards Physics-informed Deep Learning for Turbulent Flow Predictioncited by 203
  11. 2021A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groupscited by 185
  12. 2017Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equationscited by 158
  13. 2022Respecting causality is all you need for training physics-informed neural networkscited by 154
  14. 2017Physics-guided Neural Networks (PGNN): An Application in Lake Temperature Modelingcited by 130
  15. 2020Incorporating Symmetry into Deep Dynamics Models for Improved Generalizationcited by 123
  16. 2016Extrapolation and learning equationscited by 106
  17. 2020Augmenting Physical Models with Deep Networks for Complex Dynamics Forecastingcited by 93
  18. 2019Masked Gradient-Based Causal Structure Learningcited by 89
  19. 2018Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systemscited by 88
  20. 2017Causal Structure Learningcited by 84
  21. 2022Lie Point Symmetry Data Augmentation for Neural PDE Solverscited by 76
  22. 2022Causal Discovery in Heterogeneous Environments Under the Sparse Mechanism Shift Hypothesiscited by 54
  23. 2022Generalizing to New Physical Systems via Context-Informed Dynamics Modelcited by 49
  24. 2021Meta-Learning Dynamics Forecasting Using Task Inferencecited by 37
  25. 2020Causal models for dynamical systemscited by 34
  26. 2016From Deterministic ODEs to Dynamic Structural Causal Modelscited by 32
  27. 2020Bridging Physics-based and Data-driven modeling for Learning Dynamical Systemscited by 25
  28. 2020Neural Dynamical Systems: Balancing Structure and Flexibility in Physical Predictioncited by 18
  29. 2018Deep learning algorithm for data-driven simulation of noisy dynamical systemcited by 12
  30. 2020Learning Symbolic Expressions via Gumbel-Max Equation Learner Networkscited by 8

Built on by

Cited by year

Citing papers per year: 2024: 4; 2025: 2.

6 papers.

  1. 2024Out-of-Domain Generalization in Dynamical Systems Reconstructioncited by 33
  2. 2024Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Datacited by 14
  3. 2024SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equationscited by 13
  4. 2024ODE Discovery for Longitudinal Heterogeneous Treatment Effects Inferencecited by 12
  5. 2025Data-driven Discovery of Digital Twins in Biomedical Researchcited by 2
  6. 2025Learning where to learn: Training data distribution optimization for scientific machine learningcited by 1