Graph Models

Graph Attention Network

Introduced by Veličković et al. in Graph Attention Networks

A Graph Attention Network (GAT) is a neural network architecture that operates 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, a GAT enables (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.

See here for an explanation by DGL.

Source: Graph Attention Networks


Paper Code Results Date Stars


Task Papers Share
Graph Attention 58 23.67%
Node Classification 29 11.84%
Graph Learning 8 3.27%
Link Prediction 8 3.27%
Graph Classification 7 2.86%
Knowledge Graphs 6 2.45%
Benchmarking 5 2.04%
General Classification 5 2.04%
Recommendation Systems 4 1.63%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign