Global-Local Graph Neural Networks for Node-Classification
This work addresses node classification in graph learning, offering an incremental improvement by integrating global label information into existing GNN frameworks.
The paper tackles graph node classification by incorporating both global and local information through a method called Global-Local Graph Neural Networks (GLGNN), which learns label features to enhance similarity with nodes of the same label and distance from others, resulting in improved baseline performance across three GNN backbones.
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.