Graph Attention Networks

TL;DR

Graph Attention Networks (GATs) introduce a novel neural network architecture for graph data that uses masked self-attention to weigh node neighborhoods, improving flexibility and performance over prior spectral methods.

Contribution

GATs provide a new attention-based approach for graph neural networks that is scalable, inductive, and achieves state-of-the-art results on multiple benchmarks.

Findings

Achieved or matched state-of-the-art results on citation datasets.

Effective on both inductive and transductive tasks.

Eliminated need for costly matrix operations.

Abstract

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 or matched state-of-the-art results across four established transductive and inductive graph benchmarks: the Cora, Citeseer and Pubmed citation network datasets, as well as a protein-protein interaction dataset (wherein test graphs remain unseen during training).