GraphNetCore.jl is a software package for the Julia programming language that provides an the core functionality of the MeshGraphNets.jl package. Some parts are based on the implementation of the MeshGraphNets framework by Google DeepMind for simulating mesh-based physical systems via graph neural networks:
Tobias Pfaff, Meire Fortunato, Alvaro Sanchez-Gonzalez, and Peter W. Battaglia. 2021. Learning Mesh-Based Simulation with Graph Networks. In International Conference on Learning Representations.
Coming soon!
This repository uses mixed licensing:
- Original GraphNetCore.jl code and modifications are licensed under the MIT License.
- Portions adapted from Google DeepMind's MeshGraphNets remain subject to the Apache License 2.0.
See NOTICE for attribution, modification notices, and the original source.