pyg-team/pytorch_geometric
Graph Neural Network Library for PyTorch
This tool helps machine learning engineers and researchers build and train Graph Neural Networks (GNNs) for analyzing structured data. It takes graph-structured data (like social networks, molecular structures, or citation graphs) as input and produces trained GNN models capable of tasks such as classifying nodes, predicting links, or generating new graphs. It is designed for those already familiar with PyTorch.
23,561 stars. Used by 42 other packages. Actively maintained with 20 commits in the last 30 days. Available on PyPI.
Use this if you are a machine learning practitioner working with PyTorch and need a robust, flexible, and comprehensive library to develop or apply Graph Neural Networks to your structured datasets.
Not ideal if you are looking for a no-code solution or are unfamiliar with machine learning frameworks like PyTorch.
Stars
23,561
Forks
3,967
Language
Python
License
MIT
Category
Last pushed
Mar 09, 2026
Commits (30d)
20
Dependencies
9
Reverse dependents
42
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pyg-team/pytorch_geometric"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Recent Releases
Compare
Related frameworks
a-r-j/graphein
Protein Graph Library
raamana/graynet
Subject-wise networks from structural MRI, both vertex- and voxel-wise features (thickness, GM...
pykale/pykale
Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for...
dmlc/dgl
Python package built to ease deep learning on graph, on top of existing DL frameworks.
graspologic-org/graspologic
Python package for graph statistics