DGL is built atop of popular Deep Learning frameworks such as Pytorch and Apache MXNet.
Latest Updates
Keep track of what's new in DGL, such as important bug fixes, new features, new releases, etc.
See All UpdatesVisit Blogs
Deep learning on graphs is very new direction. We use blogs to introduce new ideas and researches of this area and explains how DGL can support them very easily.
Read All BlogsJoin Discussion
Got questions? Interested in contributing? or simply want to know what others are playing with? Use our forum for all kinds of discussion.
Visit Our ForumHighlighted Features
No Migration Cost
Smooth Learning Curve
Learning DGL is a blink. The powerful user-defined functions are both flexible and easy to use.
High performance
DGL automatically batches deep neural network training on one or many graphs together to achieve max efficiency.
Feedback from community
Brought to you by NYU, NYU-Shanghai, and Amazon AWS.
By far the cleanest and most elegant library for graph neural networks in PyTorch. Highly recommended! Unifies Capsule Nets (GNNs on bipartite graphs) and Transformers (GCNs with attention on fully-connected graphs) in a single API.
I taught my students Deep Graph Library (DGL) in my lecture on "Graph Neural Networks" today. It is a great resource to develop GNNs with PyTorch.