EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

FedEnD: Communication-efficient Federated Learning for non-IID data via decentralized ensemble distillation

Enrique Tomás Martínez Beltrán, Philip Giryes, Gérôme Bovet, Burkhard Stiller, Gregorio Martínez Pérez, Alberto Huertas Celdrán

Future Generation Computer Systems · 2026-10 · 183 · 108528

DOI: 10.1016/j.future.2026.108528 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Future Generation Computer Systems, 2026-10. Verfasst von Enrique Tomás Martínez Beltrán und 5 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Fundacion Seneca, University of Zurich, Comunidad Autónoma de la Región de Murcia.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Förderung

  • Fundacion Seneca
  • University of Zurich
  • Comunidad Autónoma de la Región de Murcia
  • European Defence Fund
  • European Commission

Zitieren

APA

Beltrán, E. T. M., Giryes, P., Bovet, G., Stiller, B., Pérez, G. M., & Celdrán, A. H. (2026). FedEnD: Communication-efficient Federated Learning for non-IID data via decentralized ensemble distillation. Future Generation Computer Systems, 183, 108528. https://doi.org/10.1016/j.future.2026.108528

Vancouver

Beltrán ETM, Giryes P, Bovet G, Stiller B, Pérez GM, Celdrán AH. FedEnD: Communication-efficient Federated Learning for non-IID data via decentralized ensemble distillation. Future Generation Computer Systems. 2026;183:108528. doi:10.1016/j.future.2026.108528

BibTeX
@article{Beltrn2026,
  author = {Beltrán, Enrique Tomás Martínez and Giryes, Philip and Bovet, Gérôme and Stiller, Burkhard and Pérez, Gregorio Martínez and Celdrán, Alberto Huertas},
  title = {FedEnD: Communication-efficient Federated Learning for non-IID data via decentralized ensemble distillation},
  journal = {Future Generation Computer Systems},
  year = {2026},
  volume = {183},
  pages = {108528},
  doi = {10.1016/j.future.2026.108528}
}
Kostenlos starten →