Metraipolis › archive › dc_9eb73be50269
HoTS: Homophily-Aware Temperature Scaling for Graph Neural Network Calibration — arXiv:2609.32426
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32426
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:36:34.314Z
- SHA-256 of the archived text
110ddeb7b4907a62b1e34f488ecb0028d42930b044c49ed20908da09dff85ec1- Stable URL of this page
https://metraipolis.com/documento/dc_9eb73be50269
How to cite
HoTS: Homophily-Aware Temperature Scaling for Graph Neural Network Calibration — arXiv:2609.32426 — arXiv (en), https://arxiv.org/abs/2609.32426 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9eb73be50269 (Metraipolis archive dc_9eb73be50269, sha256 110ddeb7b4907a62b1e34f488ecb0028d42930b044c49ed20908da09dff85ec1)
BibTeX
@misc{dc9eb73be50269,
title = {HoTS: Homophily-Aware Temperature Scaling for Graph Neural Network Calibration — arXiv:2609.32426},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32426},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9eb73be50269; sha256 110ddeb7b4907a62b1e34f488ecb0028d42930b044c49ed20908da09dff85ec1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32426. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
For graph node classification, calibrated class probabilities are needed when confidence scores, usually the maximum predicted class probability, are used to rank predictions, defer uncertain nodes to human review, or control risk. Existing post-hoc calibrators either apply one global temperature or use graph-aware modules without a principled structural form. We study how local graph structure should enter node-level calibration. Our first results show that a logit-only temperature rule is insufficient when nodes with identical logits but different local homophily require different optimal temperatures. We then analyze a population-concentration contextual stochastic block model with Gaussian features and a one-layer linear GCN. Under equidistant class means, the Bayes posterior over class-template scores is a temperature-scaled softmax whose inverse-temperature is governed by a homophily-dependent signal strength. In the positive-signal homophilic regime, the resulting temperature decreases approximately inversely with normalized local homophily. This law motivates Homophily-aware Temperature Scaling (HoTS), a simple post-hoc calibrator that assigns each node a positive scalar temperature from entropy-based logit concentration and estimated local homophily. HoTS has three temperature parameters, preserves the predicted class, and learns the strength of the structural correction from calibration data. Across 18 node-classification benchmarks, two GNN backbones, and eight calibration baselines, HoTS achieves the best mean Expected Calibration Error (ECE) of 4.79%, the best average rank, and the most reliable confidence ranking in selective classification. Code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.32426 — 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 2026-10-07T22:14:27.680Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).