Edge-Featured Graph Attention Network

TL;DR

This paper introduces Edge-Featured Graph Attention Networks (EGATs), which incorporate edge features into graph neural networks, enhancing their ability to learn from both node and edge information for improved graph learning tasks.

Contribution

The paper proposes EGATs, extending GATs to utilize edge features, allowing simultaneous and mutual learning of node and edge representations in graph neural networks.

Findings

EGATs outperform traditional GATs in node classification tasks.

The model effectively incorporates edge features into the learning process.

EGATs are highly competitive and applicable to edge-featured graph learning tasks.

Abstract

Lots of neural network architectures have been proposed to deal with learning tasks on graph-structured data. However, most of these models concentrate on only node features during the learning process. The edge features, which usually play a similarly important role as the nodes, are often ignored or simplified by these models. In this paper, we present edge-featured graph attention networks, namely EGATs, to extend the use of graph neural networks to those tasks learning on graphs with both node and edge features. These models can be regarded as extensions of graph attention networks (GATs). By reforming the model structure and the learning process, the new models can accept node and edge features as inputs, incorporate the edge information into feature representations, and iterate both node and edge features in a parallel but mutual way. The results demonstrate that our work is highly competitive against other node classification approaches, and can be well applied in edge-featured graph learning tasks.