Awesome Open Source
Awesome Open Source


Graph Attention Networks (Veličković et al., ICLR 2018):

GAT layer t-SNE + Attention coefficients on Cora


Here we provide the implementation of a Graph Attention Network (GAT) layer in TensorFlow, along with a minimal execution example (on the Cora dataset). The repository is organised as follows:

  • data/ contains the necessary dataset files for Cora;
  • models/ contains the implementation of the GAT network (;
  • pre_trained/ contains a pre-trained Cora model (achieving 84.4% accuracy on the test set);
  • utils/ contains:
    • an implementation of an attention head, along with an experimental sparse version (;
    • preprocessing subroutines (;
    • preprocessing utilities for the PPI benchmark (

Finally, puts all of the above together and may be used to execute a full training run on Cora.

Sparse version

An experimental sparse version is also available, working only when the batch size is equal to 1. The sparse model may be found at models/

You may execute a full training run of the sparse model on Cora through


The script has been tested running under Python 3.5.2, with the following packages installed (along with their dependencies):

  • numpy==1.14.1
  • scipy==1.0.0
  • networkx==2.1
  • tensorflow-gpu==1.6.0

In addition, CUDA 9.0 and cuDNN 7 have been used.


If you make advantage of the GAT model in your research, please cite the following in your manuscript:

  title="{Graph Attention Networks}",
  author={Veli{\v{c}}kovi{\'{c}}, Petar and Cucurull, Guillem and Casanova, Arantxa and Romero, Adriana and Li{\`{o}}, Pietro and Bengio, Yoshua},
  journal={International Conference on Learning Representations},
  note={accepted as poster},

For getting started with GATs, as well as graph representation learning in general, we highly recommend the pytorch-GAT repository by Aleksa Gordić. It ships with an inductive (PPI) example as well.

GAT is a popular method for graph representation learning, with optimised implementations within virtually all standard GRL libraries:

We recommend using either one of those (depending on your favoured framework), as their implementations have been more readily battle-tested.

Early on post-release, two unofficial ports of the GAT model to various frameworks quickly surfaced. To honour the effort of their developers as early adopters of the GAT layer, we leave pointers to them here.



Alternative Project Comparisons
Related Awesome Lists
Top Programming Languages
Top Projects

Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
Python (819,471
Network (37,636
Graph (24,390
Tensorflow (22,455
Neural Network (15,615
Keras (10,471
Attention (3,885
Sparse (2,713
Preprocessing (2,280
Attention Mechanism (775
Self Attention (128
Graph Attention Networks (53