Metraipolis › archive › dc_8bf9523b7bb4

FedDOSE: Federated Learning Framework Decomposing Site Effects for Modeling Brain Dynamic Functional Connectivity — arXiv:2608.07393

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.07393
License (as archived)
CC0-1.0
Archived
2026-10-25T01:02:44.198Z
SHA-256 of the archived text
4103336078c826dd01d500c3a5a5beb06f687f2a950a37558fe23a469d51d85f
Stable URL of this page
https://metraipolis.com/documento/dc_8bf9523b7bb4

How to cite

FedDOSE: Federated Learning Framework Decomposing Site Effects for Modeling Brain Dynamic Functional Connectivity — arXiv:2608.07393 — arXiv (en), https://arxiv.org/abs/2608.07393 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8bf9523b7bb4 (Metraipolis archive dc_8bf9523b7bb4, sha256 4103336078c826dd01d500c3a5a5beb06f687f2a950a37558fe23a469d51d85f)
BibTeX
@misc{dc8bf9523b7bb4,
  title = {FedDOSE: Federated Learning Framework Decomposing Site Effects for Modeling Brain Dynamic Functional Connectivity — arXiv:2608.07393},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.07393},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8bf9523b7bb4; sha256 4103336078c826dd01d500c3a5a5beb06f687f2a950a37558fe23a469d51d85f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07393. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Functional Magnetic Resonance Imaging ( fMRI ) data are often pooled into collaborative multi-site consortia, as deep learning models for analyses require large datasets to generalize well. While Federated Learning (FL) offers a privacy-preserving paradigm for collaborative training, standard approaches continue to struggle with statistical heterogeneity. In particular, site differences pose a key challenge in multi-site data settings. Additionally, existing FL approaches for fMRI rely on static Functional Connectivity ( FC), omitting dynamic information in brain networks. To address this, we propose FedDOSE, a novel framework that explicitly decomposes site differences for analysis of dynamic FC (dFC). FedDOSE introduces a Modularity-Guided Tucker Decomposition block to encode high-dimensional dFC tensors and capture modular-level spatio-temporal patterns efficiently. Class-specific prototypes are generated across all sites and subsequently aligned at the global level by using a combination of Optimal Transport (OT) barycenter formulation and Procrustes analysis. Extensive experiments for diagnosing Autism Spectrum Disorder (ASD) and Attention-Deficit Hyperactivity Disorder (ADHD) on three multi-site resting-state fMRI datasets: ABIDE-I, ABIDE-II, and ADHD-200, demonstrate that FedDOSE outperforms state-of-the-art methods in ASD and ADHD detection. Our results highlight its effectiveness in learning robust representations from multi-site datasets for reliable analysis.

Tema degli esploratori: scienze della vita e salute (retro-catalogo arXiv: annunci del 2026-08-10 in q-bio.NC).
Categorie arXiv: Machine Learning (cs.LG) ; Signal Processing (eess.SP); Neurons and Cognition (q-bio.NC).
Pagina del lavoro: https://arxiv.org/abs/2608.07393 — 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 2026-10-25T01:02:43.403Z dalla pagina https://arxiv.org/catchup/q-bio.NC/2026-08-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).