Metraipolis › archive › dc_60131ef6d491

Not All Nodes Are Created Equal: Homophily-Aware Stratification for Stable GNN Evaluation — arXiv:2609.19210

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.19210
License (as archived)
CC0-1.0
Archived
2026-10-10T03:22:34.998Z
SHA-256 of the archived text
2fc0fc0c641f65e4cd652967d85b2ba646382f502a746b25161389de3c74b602
Stable URL of this page
https://metraipolis.com/documento/dc_60131ef6d491

How to cite

Not All Nodes Are Created Equal: Homophily-Aware Stratification for Stable GNN Evaluation — arXiv:2609.19210 — arXiv (en), https://arxiv.org/abs/2609.19210 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_60131ef6d491 (Metraipolis archive dc_60131ef6d491, sha256 2fc0fc0c641f65e4cd652967d85b2ba646382f502a746b25161389de3c74b602)
BibTeX
@misc{dc60131ef6d491,
  title = {Not All Nodes Are Created Equal: Homophily-Aware Stratification for Stable GNN Evaluation — arXiv:2609.19210},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19210},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_60131ef6d491; sha256 2fc0fc0c641f65e4cd652967d85b2ba646382f502a746b25161389de3c74b602},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19210. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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, and folds that differ in their distribution of local neighbourhood homophily expose the model to systematically different relational conditions that directly affect message-passing behaviour. The resulting cross-fold variation reflects the homophily composition of each split, inflating reported variance beyond what model behaviour alone would produce. To address this, we propose \hp{}, a topology-aware stratification procedure that treats node homophily as the primary stratification axis, aligning folds with respect to local relational consistency alongside the class marginal that standard stratification already controls. Stratifying on homophily alone does not guarantee class balance, so \hp{} incorporates class label as a secondary axis, preserving class representativeness as a natural consequence of the procedure. We evaluate \hp{} on a broad benchmark suite comprising 15 node-classification datasets spanning the full homophily spectrum and 7 GNN architectures. \hp{} achieves a mean stability rank of 1.49 compared to 2.31 for random $k$-fold, achieving the lowest mean stability rank on 13 of 15 datasets while preserving class balance close to class-stratified splits and substantially better than random. We argue that homophily-aware split construction merits broader adoption for GNN evaluation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.AI).
Categorie arXiv: Social and Information Networks (cs.SI) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.19210 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-10T03:04:13.776Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).