When Brain Networks Travel: Learning Beyond Site

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Yingxu, Zhang, Kunyu, Yang, Yanwu, Wolfers, Thomas, Wu, Yujie, Gao, Siyang, Yin, Nan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911657079341056
author Wang, Yingxu
Zhang, Kunyu
Yang, Yanwu
Wolfers, Thomas
Wu, Yujie
Gao, Siyang
Yin, Nan
author_facet Wang, Yingxu
Zhang, Kunyu
Yang, Yanwu
Wolfers, Thomas
Wu, Yujie
Gao, Siyang
Yin, Nan
contents Graph-based learning on functional magnetic resonance imaging (fMRI) has shown strong potential for brain network analysis. However, existing methods degrade under cross-site out-of-distribution (OOD) settings because site-conditioned confounders induce non-pathological shortcuts, while functional connectivity constructed by temporal averaging obscures transient neurodynamics, limiting generalization to unseen sites. In this paper, we propose Cross-site OOD Robust brain nEtwork (CORE), a unified framework for brain network learning across unseen sites. CORE first performs site-aware confounder decoupling to mitigate site-conditioned bias and extract a cross-site population scaffold of reproducible diagnostic connectivity edges. It then profiles transient pathway dynamics over this scaffold using lightweight temporal descriptors and organizes scaffold edges into a line graph for transferable pathway-level modeling. Finally, CORE introduces a prior-guided subject-adaptive gating mechanism that leverages scaffold-derived population priors while preserving subject-specific connectivity variability. Extensive experiments under leave-one-site-out evaluation on real-world datasets (ABIDE, REST-meta-MDD, SRPBS, and ABCD) show that CORE consistently outperforms state-of-the-art baselines, with up to 6.7% relative gain. Furthermore, CORE remains robust to atlas variations, maintaining performance gains across different brain parcellation schemes.
format Preprint
id arxiv_https___arxiv_org_abs_2605_06050
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle When Brain Networks Travel: Learning Beyond Site
Wang, Yingxu
Zhang, Kunyu
Yang, Yanwu
Wolfers, Thomas
Wu, Yujie
Gao, Siyang
Yin, Nan
Machine Learning
Graph-based learning on functional magnetic resonance imaging (fMRI) has shown strong potential for brain network analysis. However, existing methods degrade under cross-site out-of-distribution (OOD) settings because site-conditioned confounders induce non-pathological shortcuts, while functional connectivity constructed by temporal averaging obscures transient neurodynamics, limiting generalization to unseen sites. In this paper, we propose Cross-site OOD Robust brain nEtwork (CORE), a unified framework for brain network learning across unseen sites. CORE first performs site-aware confounder decoupling to mitigate site-conditioned bias and extract a cross-site population scaffold of reproducible diagnostic connectivity edges. It then profiles transient pathway dynamics over this scaffold using lightweight temporal descriptors and organizes scaffold edges into a line graph for transferable pathway-level modeling. Finally, CORE introduces a prior-guided subject-adaptive gating mechanism that leverages scaffold-derived population priors while preserving subject-specific connectivity variability. Extensive experiments under leave-one-site-out evaluation on real-world datasets (ABIDE, REST-meta-MDD, SRPBS, and ABCD) show that CORE consistently outperforms state-of-the-art baselines, with up to 6.7% relative gain. Furthermore, CORE remains robust to atlas variations, maintaining performance gains across different brain parcellation schemes.
title When Brain Networks Travel: Learning Beyond Site
topic Machine Learning
url https://arxiv.org/abs/2605.06050