Hamiltonian Graph Networks with ODE Integrators

09/27/2019
by   Alvaro Sanchez-Gonzalez, et al.
0

We introduce an approach for imposing physically informed inductive biases in learned simulation models. We combine graph networks with a differentiable ordinary differential equation integrator as a mechanism for predicting future states, and a Hamiltonian as an internal representation. We find that our approach outperforms baselines without these biases in terms of predictive accuracy, energy accuracy, and zero-shot generalization to time-step sizes and integrator orders not experienced during training. This advances the state-of-the-art of learned simulation, and in principle is applicable beyond physical domains.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/10/2022

Unravelling the Performance of Physics-informed Graph Neural Networks for Dynamical Systems

Recently, graph neural networks have been gaining a lot of attention to ...
research
09/22/2022

Enhancing the Inductive Biases of Graph Neural ODE for Modeling Dynamical Systems

Neural networks with physics based inductive biases such as Lagrangian n...
research
04/28/2020

VIGN: Variational Integrator Graph Networks

Rich, physically-informed inductive biases play an imperative role in ac...
research
09/12/2019

Learning Symbolic Physics with Graph Networks

We introduce an approach for imposing physically motivated inductive bia...
research
12/16/2021

Constraint-based graph network simulator

In the rapidly advancing area of learned physical simulators, nearly all...
research
06/24/2021

Hamiltonian-based Neural ODE Networks on the SE(3) Manifold For Dynamics Learning and Control

Accurate models of robot dynamics are critical for safe and stable contr...

Please sign up or login with your details

Forgot password? Click here to reset