# TensorFlow GNN
**This is an early (alpha) release to get community feedback.** It's under
active development and **we may break API compatibility in the future**.
TensorFlow GNN is a library to build Graph Neural Networks on the TensorFlow
platform. It contains the following components:
* A high-level Keras-style API to create GNN models that can easily be composed
with other types of models. GNNs are often used in combination with ranking,
deep-retrieval (dual-encoders) or mixed with other types of models
(image, text, etc.)
* GNN API for heterogeneous graphs. Many of the graph problems we approach at
Google and in the real world contain different types of nodes and edges.
Hence the emphasis in heterogeneous models.
* A well-defined schema to declare the topology of a graph, and tools to
validate it. It describes the shape of its training data and serves to guide
other tools.
* A GraphTensor composite tensor type which holds graph data, can be batched,
and has efficient graph manipulation functionality available.
* A library of operations on the GraphTensor structure:
* Various efficient broadcast and pooling operations on nodes and edges, and
related tools.
* A library of standard baked convolutions, that can be easily extended by
ML engineers/researchers.
* A high-level API for product engineers to quickly build GNN models without
necessarily worrying about its details.
* A set of tools used to convert graph datasets and sample from large
graphs.
* An encoding of graph-shaped training data on file, as well as a library used
to parse this data into a data structure your model can extract the various
features.
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 more details, please see our [documentation](tensorflow_gnn/docs/guide/overview.md).
For background and discussion, please see O. Ferludin et al.:
[TF-GNN: Graph Neural Networks in TensorFlow](https://arxiv.org/abs/2207.03522),
2022 (full citation below).
## Installation Instructions
##### Latest available pip wheel.
`pip install tensorflow_gnn`
##### Installation from source.
A virtual environment is highly recommended.
1. **Clone tensorflow_gnn**
> `$> git clone https://github.com/tensorflow/gnn.git tensorflow_gnn`
2. **Install TensorFlow**
TF-GNN currently uses
[tf.ExtensionTypes](https://www.tensorflow.org/api_docs/python/tf/experimental/ExtensionType),
which is a feature of TensorFlow 2.7. As such, you will need to install
TensorFlow build, following the instructions here:
https://www.tensorflow.org/install/pip.
> `$> pip install tensorflow`
3. **Install Bazel**
Bazel is required to build the source of this package. Follow the
instructions here to install Bazel for your OS:
https://docs.bazel.build/versions/main/install.html
4. **Install tensorflow_gnn**
> `$> cd tensorflow_gnn && python3 -m pip install .`
## 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
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 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 = {2022},
url = {http://arxiv.org/abs/2207.03522},
}
```
没有合适的资源?快使用搜索试试~ 我知道了~
tensorflow-gnn-0.3.0.tar.gz
0 下载量 177 浏览量
2024-03-21
12:37:08
上传
评论
收藏 326KB GZ 举报
温馨提示
Python库是一组预先编写的代码模块,旨在帮助开发者实现特定的编程任务,无需从零开始编写代码。这些库可以包括各种功能,如数学运算、文件操作、数据分析和网络编程等。Python社区提供了大量的第三方库,如NumPy、Pandas和Requests,极大地丰富了Python的应用领域,从数据科学到Web开发。Python库的丰富性是Python成为最受欢迎的编程语言之一的关键原因之一。这些库不仅为初学者提供了快速入门的途径,而且为经验丰富的开发者提供了强大的工具,以高效率、高质量地完成复杂任务。例如,Matplotlib和Seaborn库在数据可视化领域内非常受欢迎,它们提供了广泛的工具和技术,可以创建高度定制化的图表和图形,帮助数据科学家和分析师在数据探索和结果展示中更有效地传达信息。
资源推荐
资源详情
资源评论
收起资源包目录
tensorflow-gnn-0.3.0.tar.gz (182个子文件)
AUTHORS 304B
BUILD 11KB
BUILD 6KB
BUILD 3KB
BUILD 2KB
BUILD 2KB
BUILD 2KB
BUILD 2KB
BUILD 2KB
BUILD 1KB
BUILD 1KB
BUILD 1022B
BUILD 1013B
BUILD 999B
BUILD 998B
BUILD 950B
BUILD 886B
BUILD 706B
BUILD 529B
BUILD 491B
BUILD 455B
BUILD 420B
BUILD 376B
BUILD 295B
BUILD 294B
BUILD 272B
BUILD 167B
tensorflow_gnn.bzl 3KB
tfdep.bzl 493B
setup.cfg 38B
MANIFEST.in 177B
LICENSE 11KB
README.md 4KB
not-zip-safe 1B
PKG-INFO 5KB
PKG-INFO 5KB
graph_schema.proto 11KB
sampling_spec.proto 7KB
sampled_stats.proto 3KB
subgraph.proto 2KB
examples.proto 1023B
graph_tensor.py 59KB
graph_tensor_test.py 51KB
graph_tensor_ops.py 41KB
graph_tensor_ops_test.py 41KB
graph_piece.py 40KB
batching_utils.py 38KB
layers.py 33KB
layers_test.py 32KB
batching_utils_test.py 32KB
sampling_lib_test.py 31KB
layers.py 29KB
unigraph_test.py 29KB
graph_piece_test.py 28KB
graph_tensor_io_test.py 27KB
layers.py 27KB
graph_ops.py 26KB
unigraph.py 26KB
padding_ops.py 26KB
padding_ops_test.py 26KB
layers_test.py 26KB
graph_ops_test.py 25KB
graph_update.py 25KB
layers_test.py 23KB
map_features_test.py 23KB
sampling_lib.py 22KB
graph_sampler_test.py 21KB
adjacency.py 20KB
graph_tensor_io.py 20KB
convolution_base.py 19KB
convert_ogb_dataset.py 17KB
graph_sampler.py 17KB
orchestration.py 17KB
map_features.py 16KB
schema_validation.py 16KB
tensor_utils.py 16KB
subgraph_test.py 16KB
convolution_base_test.py 15KB
schema_validation_test.py 15KB
sampling_spec_builder.py 15KB
keras_e2e_test.py 14KB
datasets.py 13KB
subgraph.py 13KB
keras_tensors_test.py 13KB
adjacency_test.py 13KB
graph_tensor_random.py 13KB
schema_utils.py 12KB
gcn_conv_test.py 12KB
attribution.py 12KB
tensor_utils_test.py 11KB
gcn_conv.py 10KB
schema_utils_test.py 10KB
keras_fit.py 10KB
graph_update_test.py 10KB
next_state.py 10KB
attribution_test.py 9KB
builders_test.py 9KB
model_export_test.py 9KB
classification.py 9KB
preprocessing_common_test.py 9KB
共 182 条
- 1
- 2
资源评论
程序员Chino的日记
- 粉丝: 3718
- 资源: 5万+
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- 基于Java实现的MapReduce分布式计算框架设计源码
- Qwen2.5 Technical Report 详细技术报告
- 基于ThinkGms v2.0.1框架的旧快马配送系统设计源码
- 基于Java编程语言的俄罗斯方块游戏设计源码
- 套膜封切机工程图机械结构设计图纸和其它技术资料和技术方案非常好100%好用.zip
- 小麦联合收割机工程图机械结构设计图纸和其它技术资料和技术方案非常好100%好用.zip
- 小型全自动卷烟机构图纸工程图机械结构设计图纸和其它技术资料和技术方案非常好100%好用.zip
- 线体牵引力测试机(含bom)sw17可编辑工程图机械结构设计图纸和其它技术资料和技术方案非常好100%好用.zip
- 前端入门day1的文件记录
- 型钢校正机矫直机工程图机械结构设计图纸和其它技术资料和技术方案非常好100%好用.zip
- 旋转停车系统工程图机械结构设计图纸和其它技术资料和技术方案非常好100%好用.zip
- 数仓构造与多维分析大作业
- 【图像融合】基于matlab结合contourlet与压缩感知图像融合【含Matlab源码 9741期】.zip
- 【坐标转换】基于matlab GUI大地坐标和空间直角坐标相互转换【含Matlab源码 9227期】.zip
- 【迷宫路径规划】基于matlab SARSA和强化学习迷宫路径规划解决迷宫问题【含Matlab源码 8857期】.mp4
- 【语音去噪】基于matlab GUI切比雪夫+椭圆形低通滤波器语音去噪【含Matlab源码 2198期】.mp4
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功