Context-Aware Graph Attention Networks

TL;DR

This paper introduces CaGAT, a novel GNN model that learns context-aware attention for both node features and edge weights, improving semi-supervised learning on benchmark datasets.

Contribution

CaGAT is the first GNN to jointly learn context-aware representations for edges and nodes in a unified framework, enhancing network performance.

Findings

CaGAT outperforms existing GNNs on benchmark datasets.

Joint learning of edge and node representations improves accuracy.

Experimental results validate the effectiveness of the proposed approach.

Abstract

Graph Neural Networks (GNNs) have been widely studied for graph data representation and learning. However, existing GNNs generally conduct context-aware learning on node feature representation only which usually ignores the learning of edge (weight) representation. In this paper, we propose a novel unified GNN model, named Context-aware Adaptive Graph Attention Network (CaGAT). CaGAT aims to learn a context-aware attention representation for each graph edge by further exploiting the context relationships among different edges. In particular, CaGAT conducts context-aware learning on both node feature representation and edge (weight) representation simultaneously and cooperatively in a unified manner which can boost their respective performance in network training. We apply CaGAT on semi-supervised learning tasks. Promising experimental results on several benchmark datasets demonstrate the effectiveness and benefits of CaGAT.