GitHub repository
A comprehensive library for building and training Graph Neural Networks (GNNs) with PyTorch.
What is GitHub repository?
PyTorch Geometric (PyG) is a library built on PyTorch for implementing and training Graph Neural Networks (GNNs) on structured data like graphs, point clouds, and 3D meshes. It provides a comprehensive suite of tools, including pre-implemented GNN layers, scalable data loaders, and benchmark datasets, to simplify geometric deep learning research and applications.
Machine learning researchers and practitioners working with graph-structured data, including those in domains like chemistry (molecular graphs), social networks, recommendation systems, and 3D vision (point clouds).
Developers choose PyG for its seamless PyTorch integration, extensive collection of state-of-the-art GNN implementations, and flexibility to easily customize or create new models. Its focus on real-world scalability and comprehensive tooling makes it a go-to library for both prototyping and production-level GNN projects.
Overview
Graph Neural Network Library for PyTorch
Use Cases
Best For
- Implementing and experimenting with state-of-the-art Graph Neural Network architectures.
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
