pyg-team/pytorch_geometric
Graph Neural Network Library for PyTorch
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
Ranks #341 of 2,531 repositories GStars tracks this week (top 13%).
1 release in the last 90 days, the latest 15 days ago, with 424 contributors on GitHub.
Use Cases & Benefits
- Provides a comprehensive library to build and train Graph Neural Networks (GNNs) using PyTorch for deep learning on graph-structured and irregular data.
- Offers a unified, easy-to-use API with extensive state-of-the-art GNN models and flexible message passing interfaces for rapid research and development.
- Use for developing scalable GNN models that handle large graphs with millions of nodes and support multi-GPU training.
- Use for implementing custom GNN layers and architectures leveraging a modular message passing framework for novel research in geometric deep learning.
- Use for applying GNNs to diverse domains such as citation networks, 3D point clouds, heterogeneous graphs, and dynamic temporal graph data.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
MIT
Permissive: commercial use, modification and redistribution are allowed with attribution.
Community files
- README: present
- Contributing guide: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
PyG (PyTorch Geometric) is a library built upon PyTorch to easily write and train Graph Neural Networks (GNNs) for a wide range of applications related to structured data.
It consists of various methods for deep learning on graphs and other irregular structures, also known as geometric deep learning, from a variety of published papers. In addition, it consists of easy-to-use mini-batch loaders for operating on many small and single giant graphs, multi GPU-support,
torch.compilesupport,DataPipesupport, a large number of common benchmark datasets (based on simple interfaces to create your own), and helpful transforms, both for learning on arbitrary graphs as well as on 3D meshes or point clouds.Whether you are a machine learning researcher or first-time user of machine learning toolkits, here are some reasons to try out PyG for machine learning on graph-structured data.
In this quick tour, we highlight the ease of creating and training a GNN model with only a few lines of code.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+209 stars over 90 days across 8 snapshot days; best day +8 on Jul 25.
Forks
4.1K+65
Open issues
1.4K+78
Compared with peers in Deep Learning
Fastest-growing repositories GStars tracks in this cohort for the week of Oct 18, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| koharu-rs/koharu | 6.4K | +192 | 63 | 30 days ago |
| poloclub/transformer-explainer | 9.0K | +143 | 75 | 858 days ago |
| vllm-project/vllm | 94.9K | +0 | 75 | 3 days ago |
| pyg-team/pytorch_geometric | 24.1K | +0 | 59 | 15 days ago |
| sapientinc/HRM | 12.7K | +0 | 75 | — |
| Project-MONAI/MONAI | 8.8K | +0 | 75 | 20 days ago |
| Category median | 9.0K | +0 | 75 | — |
Discover Repositories
Search across tracked repositories by name or description