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).

READ FULL TEXT

page 1

page 2

page 3

page 4

04/17/2019

Inductive Graph Representation Learning with Recurrent Graph Neural Networks

In this paper, we study the problem of node representation learning with...
06/07/2017

Inductive Representation Learning on Large Graphs

Low-dimensional embeddings of nodes in large graphs have proved extremel...
03/14/2022

Simplicial Attention Neural Networks

The aim of this work is to introduce simplicial attention networks (SANs...
09/03/2020

Learning from Protein Structure with Geometric Vector Perceptrons

Learning on 3D structures of large biomolecules is emerging as a distinc...
06/08/2020

Graph Representation Learning Network via Adaptive Sampling

Graph Attention Network (GAT) and GraphSAGE are neural network architect...
08/12/2018

Large-Scale Learnable Graph Convolutional Networks

Convolutional neural networks (CNNs) have achieved great success on grid...
10/21/2021

FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping

While Graph Neural Networks have gained popularity in multiple domains, ...

Code Repositories

keras-gat

Keras implementation of the Graph Attention Network model by Veličković et. al (2017, https://arxiv.org/abs/1710.10903)


view repo