Global-Local Graph Neural Networks for Node-Classification

TL;DR

This paper introduces Global-Local-GNN (GLGNN), a novel approach that combines global label and node features with local information to enhance node classification accuracy in graphs.

Contribution

The paper proposes a new GNN framework that learns label features and integrates global information, improving upon traditional local-only GNNs for node classification.

Findings

GLGNN outperforms baseline models across different GNN backbones.

Utilizing global label features enhances node classification performance.

The approach demonstrates the importance of global information in GNNs.

Abstract

The task of graph node classification is often approached by utilizing a local Graph Neural Network (GNN), that learns only local information from the node input features and their adjacency. In this paper, we propose to improve the performance of node classification GNNs by utilizing both global and local information, specifically by learning label- and node- features. We therefore call our method Global-Local-GNN (GLGNN). To learn proper label features, for each label, we maximize the similarity between its features and nodes features that belong to the label, while maximizing the distance between nodes that do not belong to the considered label. We then use the learnt label features to predict the node classification map. We demonstrate our GLGNN using three different GNN backbones, and show that our approach improves baseline performance, revealing the importance of global information utilization for node classification.