Metraipolis › archive › dc_7e62e60da33e

Rethinking Epistemic Uncertainty in Node Classification through Information Growth — arXiv:2610.03418

Source
arXiv
Original
https://arxiv.org/abs/2610.03418
License (as archived)
CC0-1.0
Archived
2026-10-05T22:50:39.477Z
SHA-256 of the archived text
22d0c769c34b232c7c0d56a9a86745b6855785128e41fec11c0e8a2cae1fb8e7
Stable URL of this page
https://metraipolis.com/documento/dc_7e62e60da33e

How to cite

Rethinking Epistemic Uncertainty in Node Classification through Information Growth — arXiv:2610.03418 — arXiv, https://arxiv.org/abs/2610.03418 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e62e60da33e (Metraipolis archive dc_7e62e60da33e, sha256 22d0c769c34b232c7c0d56a9a86745b6855785128e41fec11c0e8a2cae1fb8e7)
BibTeX
@misc{dc7e62e60da33e,
  title = {Rethinking Epistemic Uncertainty in Node Classification through Information Growth — arXiv:2610.03418},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03418},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e62e60da33e; sha256 22d0c769c34b232c7c0d56a9a86745b6855785128e41fec11c0e8a2cae1fb8e7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03418. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Epistemic uncertainty should decrease as additional information about the data-generating process (DGP) becomes available to the predictor. Yet, existing graph evidential deep learning (EDL) methods for node classification typically construct epistemic uncertainty from graph-specific properties and evaluate it on downstream tasks such as out-of-distribution detection, which do not test its reducibility as information about the DGP increases. To make reducibility directly testable, we introduce a statistical framework for studying epistemic uncertainty under information growth. Our framework specifies an information-growth experimental protocol and a consistency criterion for epistemic predictors, while using projective graph DGPs to ensure that growing graphs, which in general need not provide increasing information about the same DGP, constitute coherent observations of the same underlying process. We show that EDL methods do not explicitly estimate data uncertainty arising from a single finite graph observation and instead regulate epistemic uncertainty through model hyperparameters, precluding consistency, as corroborated by controlled information-growth experiments. As an alternative, we propose graph bootstrap ensembles, capturing both data and procedural uncertainty through graph resampling and randomized training. Under the same experimental protocol, these ensembles exhibit epistemic uncertainty reduction beyond standard deep ensembles. These findings support bootstrap ensembles as candidate consistent epistemic predictors under information growth.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.03418 — 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 2026-10-05T22:45:55.859Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).