Constraint-based graph network simulator

by   Yulia Rubanova, et al.

In the rapidly advancing area of learned physical simulators, nearly all methods train forward models that directly predict future states from input states. However, many traditional simulation engines use a constraint-based approach instead of direct prediction. Here we present a framework for constraint-based learned simulation, where a scalar constraint function is implemented as a neural network, and future predictions are computed as the solutions to optimization problems under these learned constraints. We implement our method using a graph neural network as the constraint function and gradient descent as the constraint solver. The architecture can be trained by standard backpropagation. We test the model on a variety of challenging physical domains, including simulated ropes, bouncing balls, colliding irregular shapes and splashing fluids. Our model achieves better or comparable performance to top learned simulators. A key advantage of our model is the ability to generalize to more solver iterations at test time to improve the simulation accuracy. We also show how hand-designed constraints can be added at test time to satisfy objectives which were not present in the training data, which is not possible with forward approaches. Our constraint-based framework is applicable to any setting where forward learned simulators are used, and demonstrates how learned simulators can leverage additional inductive biases as well as the techniques from the field of numerical methods.


DOGE-Train: Discrete Optimization on GPU with End-to-end Training

We present a fast, scalable, data-driven approach for solving linear rel...

Learning the Dynamics of Particle-based Systems with Lagrangian Graph Neural Networks

Physical systems are commonly represented as a combination of particles,...

Learning to Simulate Complex Physics with Graph Networks

Here we present a general framework for learning simulation, and provide...

Hamiltonian Graph Networks with ODE Integrators

We introduce an approach for imposing physically informed inductive bias...

DeepSaDe: Learning Neural Networks that Guarantee Domain Constraint Satisfaction

As machine learning models, specifically neural networks, are becoming i...

Neuro-Symbolic Constraint Programming for Structured Prediction

We propose Nester, a method for injecting neural networks into constrain...

Refining neural network predictions using background knowledge

Recent work has shown logical background knowledge can be used in learni...

Please sign up or login with your details

Forgot password? Click here to reset