Metraipolis › archive › dc_61ff4e656db9

Beyond Site Agreement: Re-estimation for Brain Network Generalization — arXiv:2609.34611

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.34611
License (as archived): CC0-1.0
Archived: 2026-10-07T22:38:28.613Z
SHA-256 of the archived text: 51fec6b60d87a71881e8a2f07f2093d16653344a31a7c1b4654273f05f41b8c5
Stable URL of this page: https://metraipolis.com/documento/dc_61ff4e656db9

How to cite

Beyond Site Agreement: Re-estimation for Brain Network Generalization — arXiv:2609.34611 — arXiv (en), https://arxiv.org/abs/2609.34611 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_61ff4e656db9 (Metraipolis archive dc_61ff4e656db9, sha256 51fec6b60d87a71881e8a2f07f2093d16653344a31a7c1b4654273f05f41b8c5)

BibTeX

@misc{dc61ff4e656db9,
  title = {Beyond Site Agreement: Re-estimation for Brain Network Generalization — arXiv:2609.34611},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34611},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_61ff4e656db9; sha256 51fec6b60d87a71881e8a2f07f2093d16653344a31a7c1b4654273f05f41b8c5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34611. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Cross-site out-of-distribution (OOD) generalization in resting-state functional magnetic resonance imaging (rs-fMRI) often relies on learning task-discriminative representations from full-scan functional connectivity (FC) graphs and promoting invariance across source sites. However, FC graphs are estimated from finite, temporally correlated blood-oxygen-level-dependent (BOLD) sequences. Cross-site agreement therefore does not necessarily imply that predictive evidence remains supported under FC re-estimation within the same scan. In this paper, we propose Brain Network Re-estimation-Informed OOD Learning (BRIO), a framework that uses within-scan FC re-estimation to guide cross-site alignment. BRIO maps fullscan graphs and their re-estimates into consistently indexed connectome factors, enabling comparisons of their predictive contributions. It assesses re-estimation support from changes in these contributions relative to within-class subject variability and class separation. For each source-site pair and class, this task-calibrated support from both sites is combined with predictive relevance to form pairwise qualifications, which determine relative factor weights and overall alignment strength. Leave-one-site-out experiments on four real-world datasets (ABIDE, REST-metaMDD, SRPBS, and ABCD) show that BRIO consistently outperforms competitive baselines, with relative improvements of up to 3.8% in accuracy. These gains also persist under an alternative brain parcellation on ABIDE.

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/2609.34611 — 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 2026-10-07T22:14:28.247Z 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).