Discovering Symbolic Laws Directly from Trajectories with Hamiltonian Graph Neural Networks
Not on the map. Why?
Abstract (arXiv)
The time evolution of physical systems is described by differential equations, which depend on abstract quantities like energy and force. Traditionally, these quantities are derived as functionals based on observables such as positions and velocities. Discovering these governing symbolic laws is the key to comprehending the interactions in nature. Here, we present a Hamiltonian graph neural network (HGNN), a physics-enforced GNN that learns the dynamics of systems directly from their trajectory. We demonstrate the performance of HGNN on n-springs, n-pendulums, gravitational systems, and binary Lennard Jones systems; HGNN learns the dynamics in excellent agreement with the ground truth from small amounts of data. We also evaluate the ability of HGNN to generalize to larger system sizes, and to hybrid spring-pendulum system that is a combination of two original systems (spring and pendulum) on which the models are trained independently. Finally, employing symbolic regression on the learned HGNN, we infer the underlying equations relating the energy functionals, even for complex systems such as the binary Lennard-Jones liquid. Our framework facilitates the interpretable discovery of interaction laws directly from physical system trajectories. Furthermore, this approach can be extended to other systems with topology-dependent dynamics, such as cells, polydisperse gels, or deformable bodies.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 20 of its 44 references that are in the map. First posted on arXiv 11 Jul 2023.
Builds on
20 of 44 references.
References · 20
- 2018Neural Ordinary Differential Equationscited by 3,779
- 2020Learning to Simulate Complex Physics with Graph Networkscited by 880
- 2019Hamiltonian Neural Networkscited by 712
- 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 708
- 2019AI Feynman: a Physics-Inspired Method for Symbolic Regressioncited by 548
- 2020Lagrangian Neural Networkscited by 398
- 2020Discovering Symbolic Models from Deep Learning with Inductive Biasescited by 344
- 2019Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learningcited by 212
- 2019Hamiltonian Graph Networks with ODE Integratorscited by 108
- 2020Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraintscited by 105
- 2020Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learningcited by 79
- 2020AI Poincar'e: Machine Learning Conservation Laws from Trajectoriescited by 77
8 more
- 2023Interpretable Machine Learning for Science with PySR and SymbolicRegression.jlcited by 54
- 2020Benchmarking Energy-Conserving Neural Networks for Learning Dynamics from Datacited by 40
- 2022Deconstructing the Inductive Biases of Hamiltonian Neural Networkscited by 31
- 2022Learning Articulated Rigid Body Dynamics with Lagrangian Graph Neural Networkcited by 23
- 2022Unravelling the Performance of Physics-informed Graph Neural Networks for Dynamical Systemscited by 23
- 2022Learning the Dynamics of Particle-based Systems with Lagrangian Graph Neural Networkscited by 12
- 2021Machine-Learning Non-Conservative Dynamics for New-Physics Detectioncited by 10
- 2022Interpretable machine learning in Physicscited by 8
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.