Metraipolis › archive › dc_352ceb5b45e6

Strictly proper scoring rules for node selection tasks on graphs — arXiv:2611.03274

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03274
License (as archived)
CC0-1.0
Archived
2026-11-03T11:16:54.709Z
SHA-256 of the archived text
7826a39772add2eac997277fb2f34d79822e6a7419f8a66ff7643af44f4b6c2e
Stable URL of this page
https://metraipolis.com/documento/dc_352ceb5b45e6

How to cite

Strictly proper scoring rules for node selection tasks on graphs — arXiv:2611.03274 — arXiv (en), https://arxiv.org/abs/2611.03274 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_352ceb5b45e6 (Metraipolis archive dc_352ceb5b45e6, sha256 7826a39772add2eac997277fb2f34d79822e6a7419f8a66ff7643af44f4b6c2e)
BibTeX
@misc{dc352ceb5b45e6,
  title = {Strictly proper scoring rules for node selection tasks on graphs — arXiv:2611.03274},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03274},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_352ceb5b45e6; sha256 7826a39772add2eac997277fb2f34d79822e6a7419f8a66ff7643af44f4b6c2e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03274. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In node selection tasks, the goal is to identify a single unknown target node in a graph. We consider probabilistic supervised node selection, where the estimator outputs a probability distribution over the nodes of the graph and the ground-truth node is available for evaluation. Classical evaluation metrics for such tasks are either statistically ill-conceived or blind to the graph structure. To fill this gap, we introduce two strictly proper scoring rules that are explicitly graph-aware: the Resistance score, which is parameter-free, and the Diffusion score, which operates at an adjustable coarse-graining resolution. We show that the Diffusion score interpolates between the multi-category Brier score and a cluster-level weighted Brier score. The Resistance score generalises two classical scoring rules: the multi-category Brier score and the Ranked probability score. Applied to rooted trees, it also serves as the strictly proper version of the improper Hierarchical error distance used in hierarchical classification. In the same setting, we furthermore establish strict propriety of the Hierarchical cross-entropy family, a recently introduced separate class of hierarchy-aware scoring rules. Experiments on epidemic source detection and on ImageNet classification confirm that the proposed scores detect meaningful differences in estimation quality that classical metrics miss.

Tema degli esploratori: governance digitale e beni comuni (elenco arXiv cs.SI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Social and Information Networks (cs.SI); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2611.03274 — 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 2026-11-03T11:01:52.148Z dalla pagina https://arxiv.org/list/cs.SI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).