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.
@article{arxiv.2509.20627,
title = {Personalized Federated Dictionary Learning for Modeling Heterogeneity in Multi-site fMRI Data},
author = {Yipu Zhang and Chengshuo Zhang and Ziyu Zhou and Gang Qu and Hao Zheng and Yuping Wang and Hui Shen and Hongwen Deng},
journal= {arXiv preprint arXiv:2509.20627},
year = {2025}
}