mlsanityData to 7 Oct 2026

Metalearning generalizable dynamics from trajectories

arXiv 2301.00957 ↗First posted 3 Jan 2023cs.LG physics.comp-phcited by 9

Not on the map. Why?

Abstract (arXiv)

We present the interpretable meta neural ordinary differential equation (iMODE) method to rapidly learn generalizable (i.e., not parameter-specific) dynamics from trajectories of multiple dynamical systems that vary in their physical parameters. The iMODE method learns meta-knowledge, the functional variations of the force field of dynamical system instances without knowing the physical parameters, by adopting a bi-level optimization framework: an outer level capturing the common force field form among studied dynamical system instances and an inner level adapting to individual system instances. A priori physical knowledge can be conveniently embedded in the neural network architecture as inductive bias, such as conservative force field and Euclidean symmetry. With the learned meta-knowledge, iMODE can model an unseen system within seconds, and inversely reveal knowledge on the physical parameters of a system, or as a Neural Gauge to "measure" the physical parameters of an unseen system with observed trajectories. We test the validity of the iMODE method on bistable, double pendulum, Van der Pol, Slinky, and reaction-diffusion systems.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 19 of its 30 references that are in the map. First posted on arXiv 3 Jan 2023.

Builds on

19 of 30 references.

References · 19

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Densely Connected Convolutional Networkscited by 6,691
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2018Neural Ordinary Differential Equationscited by 3,733
  5. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
  6. 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 1,965
  7. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  8. 2020Neural Operator: Graph Kernel Network for Partial Differential Equationscited by 722
  9. 2021Learning the solution operator of parametric partial differential equations with physics-informed DeepOnetscited by 537
  10. 2019Meta-Learning with Implicit Gradientscited by 523
  11. 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
  12. 2018Meta-Learning: A Surveycited by 254
7 more
  1. 2018Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equationscited by 233
  2. 2018Discovering physical concepts with neural networkscited by 117
  3. 2020AI Poincar'e: Machine Learning Conservation Laws from Trajectoriescited by 77
  4. 2021Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptationcited by 50
  5. 2021One-Shot Transfer Learning of Physics-Informed Neural Networkscited by 49
  6. 2020Parameterized Neural Ordinary Differential Equations: Applications to Computational Physics Problemscited by 45
  7. 2021Machine-learning hidden symmetriescited by 31

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 4; 2026: 1.

9 papers.

  1. 2025Interpretable Machine Learning in Physics: A Reviewcited by 11
  2. 2023Learning noise-induced transitions by multi-scaling reservoir computingcited by 5
  3. 2025MetaSym: A Symplectic Meta-learning Framework for Physical Intelligencecited by 5
  4. 2025AI-Newton: A Concept-Driven Physical Law Discovery System without Prior Physical Knowledgecited by 5
  5. 2024System-Aware Neural ODE Processes for Few-Shot Bayesian Optimizationcited by 3
  6. 2024Learning to learn ecosystems from limited data -- a meta-learning approachcited by 2
  7. 2025Context-Aware Deep Lagrangian Networks for Model Predictive Controlcited by 2
  8. 2024Discover physical concepts and equations with machine learningcited by 1
  9. 2026Data-Driven Hamiltonian Reduction for Superconducting Qubits via Meta-Learningcited by 0