Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
TensorFlow GNN is a library to build Graph Neural Networks on the TensorFlow platform.
| Date | Stars |
|---|---|
| 2026-07-24 | 1538 |
| 2026-07-25 | 1538 |
| 2026-07-28 | 1538 |
| 2026-07-30 | 1538 |
| 2026-07-31 | 1537 |
| 2026-08-05 | 1538 |
| 2026-08-06 | 1538 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# TensorFlow GNN
## Summary
TensorFlow GNN is a library to build
[Graph Neural Networks](tensorflow_gnn/docs/guide/intro.md) on the TensorFlow platform.
It provides...
* a [`tfgnn.GraphTensor`](tensorflow_gnn/docs/guide/graph_tensor.md) type to represent
graphs with a [heterogeneous schema](tensorflow_gnn/docs/guide/schema.md), that is,
multiple types of nodes and edges;
* tools for [data preparation](tensorflow_gnn/docs/guide/data_prep.md),
notably a [graph sampler](tensorflow_gnn/docs/guide/beam_sampler.md)
to convert a huge database into a stream of reasonably-sized subgraphs for
training and inference;
* a collection of [ready-to-use models](tensorflow_gnn/models/README.md)
and Keras layers to do your own [GNN modeling](tensorflow_gnn/docs/guide/gnn_modeling.md);
* a high-level API for training [orchestration](tensorflow_gnn/docs/guide/runner.md).
This library is an OSS port of a Google-internal library used in a broad variety
of contexts, on homogeneous and heterogeneous graphs, and in conjunction with
other scalable graph mining tools.
For background, please see our
[blog post](https://blog.tensorflow.org/2024/02/graph-neural-networks-in-tensorflow.html)
and the [TF-GNN paper](https://arxiv.org/abs/2207.03522) (full citation below).
## Quickstart
Google Colab lets you run TF-GNN demos from your browser, no installation
required:
* [Molecular Graph
Classification](https://colab.research.google.com/github/tensorflow/gnn/blob/master/examples/notebooks/intro_mutag_example.ipynb)
with the MUTAG dataset.
* [Solving OGBN-MAG
end-to-end](https://colab.research.google.com/github/tensorflow/gnn/blob/master/examples/notebooks/ogbn_mag_e2e.ipynb)
trains a model on heterogeneous sampled subgraphs from the popular
[OGBN-MAG](https://ogb.stanford.edu/docs/nodeprop/#ogbn-mag) benchmark.
* [Learning shortest paths with
GraphNetworks](https://colab.research.google.com/github/tensorflow/gnn/blob/master/examples/notebooks/graph_network_shortest_path.ipynb)
demonstrates an advanced Encoder/Process/Decoder architecture for predicting
the edges of a shortest path.
For all colabs and user guides, please see the
[Documentation overview](tensorflow_gnn/docs/guide/overview.md)
page, which also links to the
[API docs](tensorflow_gnn/docs/api_docs/README.md).
## Installation Instructions
The latest stable release of TensorFlow GNN is available from
```
pip install tensorflow-gnn
```
For installation from source, see our [Developer
Guide](tensorflow_gnn/docs/guide/developer.md).
Key platform requirements (as of release 1.0):
* TensorFlow 2.12 or higher, and any GPU drivers it needs
[[instructions](https://www.tensorflow.org/install)].
(Future releases will raise the required TF version.)
* Keras v2, as traditionally included with TensorFlow 2.x.
TF-GNN does not work with the new multi-backend Keras v3.<br/>
**Users of TF2.16+ must also `pip install tf-keras` and set
TF_USE_LEGACY_KERAS=1**,
see our [Keras version](tensorflow_gnn/docs/guide/keras_version.md) guide for details.
* Apache Beam for distributed graph sampling.
* For some tests or scripts that requires tensorflow.lite it is required to
install ai-edge-litert by using `pip install ai-edge-litert`
TF-GNN is developed and tested on Linux. Running on other platforms supported
by TensorFlow may be possible.
## Citation
When referencing this library in a paper, please cite the
[TF-GNN paper](https://arxiv.org/abs/2207.03522):
```
@article{tfgnn,
author = {Oleksandr Ferludin and Arno Eigenwillig and Martin Blais and
Dustin Zelle and Jan Pfeifer and Alvaro Sanchez{-}Gonzalez and
Wai Lok Sibon Li and Sami Abu{-}El{-}Haija and Peter Battaglia and
Neslihan Bulut and Jonathan Halcrow and
Filipe Miguel Gon{\c{c}}alves de Almeida and Pedro Gonnet and
Liangze Jiang and Parth Kothari and Silvio Lattanzi and
Excerpt of 4,429 characters
Read on GitHub
267
138
101
86
Sami Abu-El-Haija · Google Research · United States
54
45
Parth Kothari
38
35
33
20
Pedro Gonnet · @google · Switzerland
9
Jan
6
5
5
5
4
TensorFlower Gardener
4
Hana Joo · https://www.linkedin.com/in/hana-joo-6a0379127/ · Germany
4
Rebecca Chen
3
3
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:ff9c99fa55161520, topic:deep-learning, topic:tensorflow