# 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 and discussion, please see O. Ferludin et al.:
[TF-GNN: Graph Neural Networks in TensorFlow](https://arxiv.org/abs/2207.03522),
2023 (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:
* TensorFlow 2.12, 2.13, 2.14 or 2.15, and any GPU drivers it needs
[[instructions](https://www.tensorflow.org/install)].
* Keras v2, as traditionally included with TensorFlow 2.x.
(TF-GNN does not work with the new multi-backend Keras v3.)
* Apache Beam for distributed graph sampling.
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
Andr{\'{e}} Linhares and Brandon Mayer and Vahab Mirrokni and
John Palowitch and Mihir Paradkar and Jennifer She and
Anton Tsitsulin and Kevin Villela and Lisa Wang and David Wong and
Bryan Perozzi},
title = {{TF-GNN:} Graph Neural Networks in TensorFlow},
journal = {CoRR},
volume = {abs/2207.03522},
year = {2023},
url = {http://arxiv.org/abs/2207.03522},
}
```
Raw data
{
"_id": null,
"home_page": "https://github.com/tensorflow/gnn",
"name": "tensorflow-gnn",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8,<4",
"maintainer_email": "",
"keywords": "tensorflow gnn graph",
"author": "Google LLC",
"author_email": "tensorflow-gnn@googlegroups.com",
"download_url": "https://files.pythonhosted.org/packages/46/16/bed31ec12f04fb5889c0fe6afb34e09e3c28d202b27372cd83890567e25d/tensorflow-gnn-1.0.2.tar.gz",
"platform": null,
"description": "# TensorFlow GNN\n\n## Summary\n\nTensorFlow GNN is a library to build\n[Graph Neural Networks](tensorflow_gnn/docs/guide/intro.md) on the TensorFlow platform.\nIt provides...\n\n * a [`tfgnn.GraphTensor`](tensorflow_gnn/docs/guide/graph_tensor.md) type to represent\n graphs with a [heterogeneous schema](tensorflow_gnn/docs/guide/schema.md), that is,\n multiple types of nodes and edges;\n * tools for [data preparation](tensorflow_gnn/docs/guide/data_prep.md),\n notably a [graph sampler](tensorflow_gnn/docs/guide/beam_sampler.md)\n to convert a huge database into a stream of reasonably-sized subgraphs for\n training and inference;\n * a collection of [ready-to-use models](tensorflow_gnn/models/README.md)\n and Keras layers to do your own [GNN modeling](tensorflow_gnn/docs/guide/gnn_modeling.md);\n * a high-level API for training [orchestration](tensorflow_gnn/docs/guide/runner.md).\n\nThis library is an OSS port of a Google-internal library used in a broad variety\nof contexts, on homogeneous and heterogeneous graphs, and in conjunction with\nother scalable graph mining tools.\n\nFor background and discussion, please see O. Ferludin et al.:\n[TF-GNN: Graph Neural Networks in TensorFlow](https://arxiv.org/abs/2207.03522),\n2023 (full citation below).\n\n## Quickstart\n\nGoogle Colab lets you run TF-GNN demos from your browser, no installation\nrequired:\n\n * [Molecular Graph\n Classification](https://colab.research.google.com/github/tensorflow/gnn/blob/master/examples/notebooks/intro_mutag_example.ipynb)\n with the MUTAG dataset.\n * [Solving OGBN-MAG\n end-to-end](https://colab.research.google.com/github/tensorflow/gnn/blob/master/examples/notebooks/ogbn_mag_e2e.ipynb)\n trains a model on heterogeneous sampled subgraphs from the popular\n [OGBN-MAG](https://ogb.stanford.edu/docs/nodeprop/#ogbn-mag) benchmark.\n * [Learning shortest paths with\n GraphNetworks](https://colab.research.google.com/github/tensorflow/gnn/blob/master/examples/notebooks/graph_network_shortest_path.ipynb)\n demonstrates an advanced Encoder/Process/Decoder architecture for predicting\n the edges of a shortest path.\n\nFor all colabs and user guides, please see the\n[Documentation overview](tensorflow_gnn/docs/guide/overview.md)\npage, which also links to the\n[API docs](tensorflow_gnn/docs/api_docs/README.md).\n\n## Installation Instructions\n\nThe latest stable release of TensorFlow GNN is available from\n\n```\npip install tensorflow_gnn\n```\n\nFor installation from source, see our [Developer\nGuide](tensorflow_gnn/docs/guide/developer.md).\n\nKey platform requirements:\n\n * TensorFlow 2.12, 2.13, 2.14 or 2.15, and any GPU drivers it needs\n [[instructions](https://www.tensorflow.org/install)].\n * Keras v2, as traditionally included with TensorFlow 2.x.\n (TF-GNN does not work with the new multi-backend Keras v3.)\n * Apache Beam for distributed graph sampling.\n\nTF-GNN is developed and tested on Linux. Running on other platforms supported\nby TensorFlow may be possible.\n\n## Citation\n\nWhen referencing this library in a paper, please cite the\n[TF-GNN paper](https://arxiv.org/abs/2207.03522):\n\n```\n@article{tfgnn,\n author = {Oleksandr Ferludin and Arno Eigenwillig and Martin Blais and\n Dustin Zelle and Jan Pfeifer and Alvaro Sanchez{-}Gonzalez and\n Wai Lok Sibon Li and Sami Abu{-}El{-}Haija and Peter Battaglia and\n Neslihan Bulut and Jonathan Halcrow and\n Filipe Miguel Gon{\\c{c}}alves de Almeida and Pedro Gonnet and\n Liangze Jiang and Parth Kothari and Silvio Lattanzi and \n Andr{\\'{e}} Linhares and Brandon Mayer and Vahab Mirrokni and\n John Palowitch and Mihir Paradkar and Jennifer She and\n Anton Tsitsulin and Kevin Villela and Lisa Wang and David Wong and\n Bryan Perozzi},\n title = {{TF-GNN:} Graph Neural Networks in TensorFlow},\n journal = {CoRR},\n volume = {abs/2207.03522},\n year = {2023},\n url = {http://arxiv.org/abs/2207.03522},\n}\n```\n",
"bugtrack_url": null,
"license": "Apache 2.0",
"summary": "A library for building scalable graph neural networks in TensorFlow.",
"version": "1.0.2",
"project_urls": {
"Download": "https://github.com/tensorflow/gnn.git",
"Homepage": "https://github.com/tensorflow/gnn"
},
"split_keywords": [
"tensorflow",
"gnn",
"graph"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "2f4b19c695bd4e9a3325c63f1daf4636a7f3eb4c81319fe04c3e1a94424fffee",
"md5": "b804af9e01e88de2345f65038be27d25",
"sha256": "ca908b9568ecbb57577f90509d2986222331f8df0878b4cbd493233549a25714"
},
"downloads": -1,
"filename": "tensorflow_gnn-1.0.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "b804af9e01e88de2345f65038be27d25",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8,<4",
"size": 838404,
"upload_time": "2024-02-06T17:54:59",
"upload_time_iso_8601": "2024-02-06T17:54:59.347399Z",
"url": "https://files.pythonhosted.org/packages/2f/4b/19c695bd4e9a3325c63f1daf4636a7f3eb4c81319fe04c3e1a94424fffee/tensorflow_gnn-1.0.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "4616bed31ec12f04fb5889c0fe6afb34e09e3c28d202b27372cd83890567e25d",
"md5": "1860391a8d27279c12c1358ffc7ebaad",
"sha256": "9f0416d47754d85c6c26026a7e899c0decd182f34da183f482c668cf9d58b7cb"
},
"downloads": -1,
"filename": "tensorflow-gnn-1.0.2.tar.gz",
"has_sig": false,
"md5_digest": "1860391a8d27279c12c1358ffc7ebaad",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8,<4",
"size": 637617,
"upload_time": "2024-02-06T17:55:02",
"upload_time_iso_8601": "2024-02-06T17:55:02.384432Z",
"url": "https://files.pythonhosted.org/packages/46/16/bed31ec12f04fb5889c0fe6afb34e09e3c28d202b27372cd83890567e25d/tensorflow-gnn-1.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-02-06 17:55:02",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "tensorflow",
"github_project": "gnn",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "tensorflow-gnn"
}
JSON
