PyTorch Geometric
by PyTorch · open-source · Last verified 2026-04-06
PyTorch Geometric (PyG) is a library built upon PyTorch to facilitate the development of graph neural networks (GNNs). It provides data handling utilities, learning methods on graphs and other irregular structures, and benchmark datasets for various graph-related tasks.
https://pytorch-geometric.readthedocs.io/en/latest/ ↗A
A—Great
Adoption: AQuality: A+Freshness: B+Citations: AEngagement: B+
Specifications
- License
- MIT
- Pricing
- open-source
- Capabilities
- graph data handling, GNN model implementation, graph classification, node classification, link prediction
- Integrations
- PyTorch, CUDA
- Use Cases
- social network analysis, drug discovery, recommender systems, knowledge graph reasoning, computer vision
- API Available
- Yes
- Tags
- graph neural networks, pytorch, geometric deep learning, graph data, message passing
- Added
- 2026-04-06
- Completeness
- 100%
Index Score
81.8Adoption
80
Quality
90
Freshness
75
Citations
85
Engagement
70