Graph Attention Networks

10/30/2017 ∙ by Petar Veličković, et al. ∙ 0

We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations. By stacking layers in which nodes are able to attend over their neighborhoods' features, we enable (implicitly) specifying different weights to different nodes in a neighborhood, without requiring any kind of costly matrix operation (such as inversion) or depending on knowing the graph structure upfront. In this way, we address several key challenges of spectral-based graph neural networks simultaneously, and make our model readily applicable to inductive as well as transductive problems. Our GAT models have achieved state-of-the-art results across three established transductive and inductive graph benchmarks: the Cora and Citeseer citation network datasets, as well as a protein-protein interaction dataset (wherein test graphs are entirely unseen during training).



There are no comments yet.


page 1

page 2

page 3

page 4

Code Repositories


Keras implementation of the Graph Attention Network model by Veličković et. al (2017,

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.