{"ID":2865684,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.20627","arxiv_id":"2509.20627","title":"Personalized Federated Dictionary Learning for Modeling Heterogeneity in Multi-site fMRI Data","abstract":"Data privacy constraints pose significant challenges for large-scale neuroimaging analysis, especially in multi-site functional magnetic resonance imaging (fMRI) studies, where site-specific heterogeneity leads to non-independent and identically distributed (non-IID) data. These factors hinder the development of generalizable models. To address these challenges, we propose Personalized Federated Dictionary Learning (PFedDL), a novel federated learning framework that enables collaborative modeling across sites without sharing raw data. PFedDL performs independent dictionary learning at each site, decomposing each site-specific dictionary into a shared global component and a personalized local component. The global atoms are updated via federated aggregation to promote cross-site consistency, while the local atoms are refined independently to capture site-specific variability, thereby enhancing downstream analysis. Experiments on the ABIDE dataset demonstrate that PFedDL outperforms existing methods in accuracy and robustness across non-IID datasets.","short_abstract":"Data privacy constraints pose significant challenges for large-scale neuroimaging analysis, especially in multi-site functional magnetic resonance imaging (fMRI) studies, where site-specific heterogeneity leads to non-independent and identically distributed (non-IID) data. These factors hinder the development of genera...","url_abs":"https://arxiv.org/abs/2509.20627","url_pdf":"https://arxiv.org/pdf/2509.20627v1","authors":"[\"Yipu Zhang\",\"Chengshuo Zhang\",\"Ziyu Zhou\",\"Gang Qu\",\"Hao Zheng\",\"Yuping Wang\",\"Hui Shen\",\"Hongwen Deng\"]","published":"2025-09-25T00:01:02Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false}