May 2, 2019

1327 words 7 mins read



Geometric Deep Learning Extension Library for PyTorch

repo name rusty1s/pytorch_geometric
repo link
language Python
size (curr.) 2633 kB
stars (curr.) 6797
created 2017-10-06
license MIT License

PyPI Version Build Status Docs Status Code Coverage Contributing

Documentation | Paper | External Resources

PyTorch Geometric (PyG) is a geometric deep learning extension library for PyTorch.

It consists of various methods for deep learning on graphs and other irregular structures, also known as geometric deep learning, from a variety of published papers. In addition, it consists of an easy-to-use mini-batch loader for many small and single giant graphs, multi gpu-support, a large number of common benchmark datasets (based on simple interfaces to create your own), and helpful transforms, both for learning on arbitrary graphs as well as on 3D meshes or point clouds.

PyTorch Geometric makes implementing Graph Neural Networks a breeze (see here for the accompanying tutorial). For example, this is all it takes to implement the edge convolutional layer:

import torch
from torch.nn import Sequential as Seq, Linear as Lin, ReLU
from torch_geometric.nn import MessagePassing

class EdgeConv(MessagePassing):
    def __init__(self, F_in, F_out):
        super(EdgeConv, self).__init__(aggr='max')  # "Max" aggregation.
        self.mlp = Seq(Lin(2 * F_in, F_out), ReLU(), Lin(F_out, F_out))

    def forward(self, x, edge_index):
        # x has shape [N, F_in]
        # edge_index has shape [2, E]
        return self.propagate(edge_index, x=x)  # shape [N, F_out]

    def message(self, x_i, x_j):
        # x_i has shape [E, F_in]
        # x_j has shape [E, F_in]
        edge_features =[x_i, x_j - x_i], dim=1)  # shape [E, 2 * F_in]
        return self.mlp(edge_features)  # shape [E, F_out]

In detail, the following methods are currently implemented:

Head over to our documentation to find out more about installation, data handling, creation of datasets and a full list of implemented methods, transforms, and datasets. For a quick start, check out our examples in the examples/ directory.

If you notice anything unexpected, please open an issue and let us know. If you are missing a specific method, feel free to open a feature request. We are motivated to constantly make PyTorch Geometric even better.


We provide pip wheels for all major OS/PyTorch/CUDA combinations, see here.

cpu cu92 cu100 cu101

To install the binaries, first ensure that PyTorch 1.4.0 is installed, e.g.:

$ python -c "import torch; print(torch.__version__)"
>>> 1.4.0

Then run

$ pip install torch-scatter==latest+${CUDA} -f
$ pip install torch-sparse==latest+${CUDA} -f
$ pip install torch-cluster==latest+${CUDA} -f
$ pip install torch-spline-conv==latest+${CUDA} -f
$ pip install torch-geometric

where ${CUDA} should be replaced by either cpu, cu92, cu100 or cu101 depending on your PyTorch installation.

Running examples

$ cd examples
$ python


Please cite our paper (and the respective papers of the methods used) if you use this code in your own work:

  title={Fast Graph Representation Learning with {PyTorch Geometric}},
  author={Fey, Matthias and Lenssen, Jan E.},
  booktitle={ICLR Workshop on Representation Learning on Graphs and Manifolds},

Feel free to email us if you wish your work to be listed in the external resources.

Running tests

$ python test
comments powered by Disqus