google-deepmind/graph_nets

Build Graph Nets in Tensorflow

48
/ 100
Emerging

Provides modular abstractions for graph neural networks with separate learnable functions for edge, node, and global-level attribute updates, integrated with Sonnet for flexible model composition. Supports iterative message-passing refinement across graph structure, enabling tasks like shortest-path reasoning, sorting, and physics prediction through a unified architecture. Compatible with TensorFlow 1.x and 2.x across CPU/GPU backends.

5,396 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

5,396

Forks

780

Language

Python

License

Apache-2.0

Last pushed

Dec 12, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/google-deepmind/graph_nets"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.