Metraipolis › archive › dc_be074268d074

Data Amount Heterogeneity Improves Performance in Federated Learning for Neuroimaging — arXiv:2610.38172

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.38172
License (as archived)
CC0-1.0
Archived
2026-11-01T02:23:26.471Z
SHA-256 of the archived text
0ed256d9a6371667ecebebc98697f058bdf631d4d8174f58113f2c8ea603eb11
Stable URL of this page
https://metraipolis.com/documento/dc_be074268d074

How to cite

Data Amount Heterogeneity Improves Performance in Federated Learning for Neuroimaging — arXiv:2610.38172 — arXiv (en), https://arxiv.org/abs/2610.38172 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_be074268d074 (Metraipolis archive dc_be074268d074, sha256 0ed256d9a6371667ecebebc98697f058bdf631d4d8174f58113f2c8ea603eb11)
BibTeX
@misc{dcbe074268d074,
  title = {Data Amount Heterogeneity Improves Performance in Federated Learning for Neuroimaging — arXiv:2610.38172},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.38172},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_be074268d074; sha256 0ed256d9a6371667ecebebc98697f058bdf631d4d8174f58113f2c8ea603eb11},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38172. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Federated Learning (FL) allows for secure analysis of distributed data without data sharing. We and others have successfully applied FL to neuroimaging tasks, such as Alzheimer's disease classification from structural magnetic resonance imaging (MRI). FL trains a deep learning model locally at each site, encrypts the local model parameters and sends them to a federation controller that aggregates the local models under homomorphic encryption, the resulting community model is sent back to the sites for further training, and the process repeats for a number of rounds. FL often achieves learning performance (e.g., accuracy) close to centralized training, but no data leaves the sites and model parameters are protected through encryption and other measures. In this paper, we show that federations composed of sites with heterogeneous amounts of data (1 large site plus small sites) perform better than homogeneous (same data per site) federations, particularly in low data regimes, while reaching performance close to centralized training. Having a big site often results in faster convergence and higher final accuracy. Heterogeneous federations better exploit sites with small amounts of data, a common situation in large consortia such as ENIGMA.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV); Neurons and Cognition (q-bio.NC).
Pagina del lavoro: https://arxiv.org/abs/2610.38172 — 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 2026-11-01T02:12:44.107Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).