SOURCE-LINKED INTELLIGENCE

Not All Nodes Are Created Equal: Homophily-Aware Stratification for Stable GNN Evaluation

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Graph neural networks are widely used for transductive node classification, with accuracy typically measured on randomly drawn train/validation/test splits. Reported accuracy has been shown to shift substantially across different random splits of the same dataset, making published comparisons between architectures unreliable. The classical remedy in non-graph settings is stratified $k$-fold cross-validation, which ensures each test fold reflects the full class distribution of the dataset. We argue that class stratification alone is insufficient for graphs: nodes are not isolated but connected,

Read original source ↗ Open in workspace

recordType

paper

region

Global