Graph Neural Network library for PyTorch
ptgnn: A PyTorch GNN Library
This is a library containing pyTorch code for creating graph neural network (GNN) models. The library provides some sample implementations.
ptgnn takes care of defining the whole pipeline, including data wrangling tasks, such
as data loading and tensorization. It also defines PyTorch
the neural network operations. These are independent of the
AbstractNeuralModels and can be used as all other PyTorch's
if one wishes to do so.
The library is mainly engineered to be fast for sparse graphs. For example, for the
Graph2Class task (discussed below) on a V100 with the default hyperparameters and architecture
ptgnn can process about 82 graphs/sec (209k nodes/sec and 1,129k edges/sec) during training
and about 200 graph/sec (470k nodes/sec and 2,527k edges/sec) during testing.
All task implementations can be found in the
Detailed instructions on the data and the training steps can be found here.
We welcome external contributions. The following GNN-based tasks are implemented:
- PPI The PPI task as described by Zitnik and Leskovec, 2017.
- VarMisuse This is a re-implementation of the VariableMisuse task of Allamanis et al., 2018.
- Graph2Sequence This is re-implementation of the GNN->GRU model of Fernandes et. al., 2019.
- Graph2Class Classify (Label) a subset of the input nodes into classes similar to Graph2Class in Typilus.
The tutorial gives a step-by-step example for coding the Graph2Class model.
This code was tested with PyTorch 1.4 and depends
Please install the appropriate versions of these libraries based
on your CUDA setup following their instructions. (Note
pytorch-scatter binaries built for CUDA 10.1 also work for
To install PyTorch 1.4, use the up-to-date command from PyTorch Get Started, selecting the appropriate options, e.g. for Linux, pip, and CUDA 10.1 it's currently:
pip install torch torchvision
pytorch-scatter, follow the instructions from the GitHub repo, choosing the appropriate CUDA option, e.g., for CUDA 10.1:
pip install torch-scatter==2.0.4+cu101 -f https://pytorch-geometric.com/whl/torch-1.4.0.html
ptgnnfrom pypi, including all other dependencies:
pip install ptgnn
If you want to use ptgnn sampels with Azure ML (e.g. the
--amlflag in the implementation CLIs), install with
pip install ptgnn[aml]
or directly from the sources,
cdinto the root directory of the project and run
pip install -e .
To check that installation was successful and run the unit tests:
python setup.py test
This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.
When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.
To contribute to this library, first follow the next steps to setup your development environment:
- Install the library requirements.
- Install the pre-commit hooks:
pip3 install pre-commit
- Install the hooks
If you are using conda, then download the correct torch-scatter wheel.
torch==1.5.0 and Python 3.7, you can use the environment.yml
included in the repo, with the following steps:
$ conda env create -f environment.yml $ conda activate ptgnn-env $ pip install torch_scatter-2.0.4+cu102-cp37-cp37m-linux_x86_64.whl $ pip install -e . $ python setup.py test $ pip install pre-commit $ pre-commit install
Releasing to PyPi
Release history Release notifications | RSS feed
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
|Filename, size||File type||Python version||Upload date||Hashes|
|Filename, size ptgnn-0.9.2-py3-none-any.whl (74.2 kB)||File type Wheel||Python version py3||Upload date||Hashes View|
|Filename, size ptgnn-0.9.2.tar.gz (68.7 kB)||File type Source||Python version None||Upload date||Hashes View|