dmlc/dgl
Python package built to ease deep learning on graph, on top of existing DL frameworks.
Deep Graph Library (DGL) helps researchers and practitioners apply deep learning to data structured as graphs. It takes graph data, which can represent anything from social networks to molecular structures, and helps you build machine learning models to make predictions or find patterns within them. This is for anyone working with interconnected data who wants to leverage advanced AI techniques.
14,245 stars. Used by 4 other packages. No commits in the last 6 months. Available on PyPI.
Use this if you need to develop, train, and apply deep learning models on large and complex graph-structured datasets, especially for tasks like node classification, link prediction, or graph classification.
Not ideal if your data is not inherently graph-structured or if you only need basic graph analysis without deep learning.
Stars
14,245
Forks
3,058
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 31, 2025
Commits (30d)
0
Dependencies
8
Reverse dependents
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dmlc/dgl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
pyg-team/pytorch_geometric
Graph Neural Network Library for PyTorch
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...
graspologic-org/graspologic
Python package for graph statistics