Here we present a machine learning framework and model implementation that
can learn to simulate a wide variety of challenging physical domains, involving
fluids, rigid solids, and deformable materials interacting with one another.
Our framework---which we term "Graph Network-based Simulators"
(GNS)---represents the state of a physical system with particles, expressed as
nodes in a graph, and computes dynamics via learned message-passing. Our
results show that our model can generalize from single-timestep predictions
with thousands of particles during training, to different initial conditions,
thousands of timesteps, and at least an order of magnitude more particles at
test time. Our model was robust to hyperparameter choices across various
evaluation metrics: the main determinants of long-term performance were the
number of message-passing steps, and mitigating the accumulation of error by
corrupting the training data with noise. Our GNS framework advances the
state-of-the-art in learned physical simulation, and holds promise for solving
a wide range of complex forward and inverse problems.
Description
[2002.09405] Learning to Simulate Complex Physics with Graph Networks
%0 Generic
%1 sanchezgonzalez2020learning
%A Sanchez-Gonzalez, Alvaro
%A Godwin, Jonathan
%A Pfaff, Tobias
%A Ying, Rex
%A Leskovec, Jure
%A Battaglia, Peter W.
%D 2020
%K available from:adulny graph_neural_network physics simulation thema thema:ba thema:physics_gn
%T Learning to Simulate Complex Physics with Graph Networks
%U http://arxiv.org/abs/2002.09405
%X Here we present a machine learning framework and model implementation that
can learn to simulate a wide variety of challenging physical domains, involving
fluids, rigid solids, and deformable materials interacting with one another.
Our framework---which we term "Graph Network-based Simulators"
(GNS)---represents the state of a physical system with particles, expressed as
nodes in a graph, and computes dynamics via learned message-passing. Our
results show that our model can generalize from single-timestep predictions
with thousands of particles during training, to different initial conditions,
thousands of timesteps, and at least an order of magnitude more particles at
test time. Our model was robust to hyperparameter choices across various
evaluation metrics: the main determinants of long-term performance were the
number of message-passing steps, and mitigating the accumulation of error by
corrupting the training data with noise. Our GNS framework advances the
state-of-the-art in learned physical simulation, and holds promise for solving
a wide range of complex forward and inverse problems.
@misc{sanchezgonzalez2020learning,
abstract = {Here we present a machine learning framework and model implementation that
can learn to simulate a wide variety of challenging physical domains, involving
fluids, rigid solids, and deformable materials interacting with one another.
Our framework---which we term "Graph Network-based Simulators"
(GNS)---represents the state of a physical system with particles, expressed as
nodes in a graph, and computes dynamics via learned message-passing. Our
results show that our model can generalize from single-timestep predictions
with thousands of particles during training, to different initial conditions,
thousands of timesteps, and at least an order of magnitude more particles at
test time. Our model was robust to hyperparameter choices across various
evaluation metrics: the main determinants of long-term performance were the
number of message-passing steps, and mitigating the accumulation of error by
corrupting the training data with noise. Our GNS framework advances the
state-of-the-art in learned physical simulation, and holds promise for solving
a wide range of complex forward and inverse problems.},
added-at = {2022-04-19T11:45:22.000+0200},
author = {Sanchez-Gonzalez, Alvaro and Godwin, Jonathan and Pfaff, Tobias and Ying, Rex and Leskovec, Jure and Battaglia, Peter W.},
biburl = {https://www.bibsonomy.org/bibtex/21c7b6054ba44bd3f3a3daea5e9698e7b/uw_ss22_ml},
description = {[2002.09405] Learning to Simulate Complex Physics with Graph Networks},
interhash = {7b2f45fdcabe38ad5ff4cf058034c089},
intrahash = {1c7b6054ba44bd3f3a3daea5e9698e7b},
keywords = {available from:adulny graph_neural_network physics simulation thema thema:ba thema:physics_gn},
note = {cite arxiv:2002.09405Comment: Accepted at ICML 2020},
timestamp = {2022-04-19T16:05:41.000+0200},
title = {Learning to Simulate Complex Physics with Graph Networks},
url = {http://arxiv.org/abs/2002.09405},
year = 2020
}