Network Science

The interplay between communities and homophily in semi-supervised classification using graph neural networks
This study investigates how community structure and homophily influence Graph Neural Networks (GNNs) in semi-supervised node classification tasks. By systematically modifying eight datasets and measuring GNN performance with and without these structural properties, we demonstrate their significant impact on classification accuracy and reveal insights about their interaction. We introduce an information-theoretic metric to quantify community-label correlation, providing practical guidelines for model selection based on graph structure. Our findings enhance understanding of GNN capabilities and improve model selection for semi-supervised node classification tasks.
Hussain Hussain, Tomislav Đuričić, Elisabeth Lex, Denis Helić, Roman Kern
PDF Cite Project DOI
The interplay between communities and homophily in semi-supervised classification using graph neural networks