dmlc/dgl

Python package built to ease deep learning on graph, on top of existing DL frameworks.

66
/ 100
Established

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.

graph-analytics network-science bioinformatics social-network-analysis recommender-systems
Stale 6m
Maintenance 2 / 25
Adoption 14 / 25
Maturity 25 / 25
Community 25 / 25

How are scores calculated?

Stars

14,245

Forks

3,058

Language

Python

License

Apache-2.0

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.