Metraipolis › archive › dc_49208d5fcd3a
Local Evidence and Geometric Readout Repair in Trained GNNs — arXiv:2609.27092
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.27092
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T09:12:09.905Z
- SHA-256 of the archived text
e50a1ff8e4608d72e471f39a976caa7621ee38f918e91fe826f6d32e22e1a246- Stable URL of this page
https://metraipolis.com/documento/dc_49208d5fcd3a
How to cite
Local Evidence and Geometric Readout Repair in Trained GNNs — arXiv:2609.27092 — arXiv (en), https://arxiv.org/abs/2609.27092 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_49208d5fcd3a (Metraipolis archive dc_49208d5fcd3a, sha256 e50a1ff8e4608d72e471f39a976caa7621ee38f918e91fe826f6d32e22e1a246)
BibTeX
@misc{dc49208d5fcd3a,
title = {Local Evidence and Geometric Readout Repair in Trained GNNs — arXiv:2609.27092},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.27092},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_49208d5fcd3a; sha256 e50a1ff8e4608d72e471f39a976caa7621ee38f918e91fe826f6d32e22e1a246},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27092. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Many node-classification GNNs apply a linear classifier to a nonnegative mixture of local messages. An error can reflect either poor mixture weights or a reachable logit set poorly positioned for the classifier. We separate these causes with an exact-mass linear program and two learned post-hoc repairs. Every reweighted prediction has an equivalent centered logit translation, but only translations in a message-induced displacement set are realizable by reweighting. Across eight datasets, eight GNN backbones, and ten splits, mean accuracy rises from 62.6% for the frozen models to 63.8% with reweighting and 65.3% with set-conditioned translation. A parameter-matched node-only translator reaches 64.6%, showing that translation explains most of the gain while the message set supplies a smaller additional benefit. Although oracle reweighting can correct many errors, label-free reweighting captures little of this potential: local evidence is often present but hard to select, and relaxing the evidence constraint is more effective than learning within it. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.27092 — 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 2026-10-08T08:13:26.616Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).