pytorch_geometric and deepsnap

PyTorch Geometric provides the core GNN primitives and layers, while DeepSnap builds on top of it as a higher-level library for converting graph data formats and integrating with PyTorch Geometric, making them complements rather than competitors.

pytorch_geometric
80
Verified
deepsnap
58
Established
Maintenance 17/25
Adoption 15/25
Maturity 25/25
Community 23/25
Maintenance 6/25
Adoption 10/25
Maturity 25/25
Community 17/25
Stars: 23,561
Forks: 3,967
Downloads:
Commits (30d): 20
Language: Python
License: MIT
Stars: 568
Forks: 56
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No risk flags
No Dependents

About pytorch_geometric

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.

graph-analytics network-science deep-learning-research structured-data-modeling bioinformatics

About deepsnap

snap-stanford/deepsnap

Python library assists deep learning on graphs

This library helps machine learning engineers and researchers build and train deep learning models on graph-structured data more efficiently. It takes in graph data, such as social networks or molecular structures, and helps prepare it for training, then outputs trained graph neural network models. The primary users are Python developers working with graph deep learning frameworks.

graph-neural-networks deep-learning machine-learning-engineering data-science graph-analytics

Scores updated daily from GitHub, PyPI, and npm data. How scores work