TensorFlow GNN

TensorFlow GNN is a library to build Graph Neural Networks on the TensorFlow platform. It is based on a library used internally by Google. APIs may change, as this is an early release to get community feedback.

Logo

../_images/tensorflow_gnn-small.png

Website

N/A

Repository

https://github.com/tensorflow/gnn

Byline

TensorFlow GNN is a library to build Graph Neural Networks on the TensorFlow platform.

License

Apache 2.0

Project age

0 years 7 months

Backers

Google (Creator and maintainer)

Lastest News (2022-07-04)

v0.2.0 Added 3 popular model architectures from literature (GATv2, GraphSAGE, and GCN) and a commonly-used MPNN architecture from within … more

Size score (1 to 10, higher is better)

2.75

Trend score (1 to 10, higher is better)

6.25

Education Resources

No recent documentation available for project.

Git Commit Statistics

Statistics computed using Git data through March 31, 2022.

Statistic

Lifetime

Last 12 Months

Commits

314

314

Lines committed

347,111

347,111

Unique committers

11

11

Core committers

4

4

../_images/tensorflow_gnn-monthly-commits.png

Similar Projects

Project

Size Score

Trend Score

Byline

DGL

5.25

6.0

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

JGraphT

5.5

3.0

JGraphT is a free Java class library that provides mathematical graph-theory objects and algorithms. It runs on Java 2 Platform (requires JDK 11 or later starting with JGraphT 1.5.0).

NetworkX

6.75

2.75

Network Analysis in Python

PyGOD

1.75

8.75

A Python Library for Graph Outlier Detection (Anomaly Detection)

kglab

4.5

4.5

A simple abstraction layer in Python for building knowledge graphs