Corpus ID: 211252550

Learning to Simulate Complex Physics with Graph Networks

@article{SanchezGonzalez2020LearningTS,
  title={Learning to Simulate Complex Physics with Graph Networks},
  author={Alvaro Sanchez-Gonzalez and Jonathan M. Godwin and Tobias Pfaff and Rex Ying and Jure Leskovec and Peter W. Battaglia},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.09405}
}
  • Alvaro Sanchez-Gonzalez, Jonathan M. Godwin, +3 authors Peter W. Battaglia
  • Published 2020
  • Mathematics, Computer Science, Physics
  • ArXiv
  • Here we present a general framework for learning simulation, and provide a single model implementation that yields state-of-the-art performance across a 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… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore key concepts

    Links to highly relevant papers for key concepts in this paper:

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 13 CITATIONS

    VIGN: Variational Integrator Graph Networks

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Accurately Solving Physical Systems with Graph Learning

    VIEW 4 EXCERPTS
    CITES BACKGROUND, METHODS & RESULTS
    HIGHLY INFLUENCED

    Forward Prediction for Physical Reasoning

    VIEW 5 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Discovering Symbolic Models from Deep Learning with Inductive Biases

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Learning Physical Graph Representations from Visual Scenes

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 38 REFERENCES

    Propagation Networks for Model-Based Control Under Partial Observation

    VIEW 2 EXCERPTS

    Learning to Control PDEs with Differentiable Physics

    VIEW 2 EXCERPTS