EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BiPruneFL: Computation and Communication Efficient Federated Learning With Binary Quantization and Pruning

Sangmin Lee, Hyeryung Jang

IEEE Access · 2025 · 13 · 42441-42456

DOI: 10.1109/access.2025.3547627 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2025. Verfasst von Sangmin Lee und 1 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, Korean Government [Ministry of Science and ICT (MSIT)], South Korea, MSIT through the Information Technology Research Center (ITRC) Support Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Förderung

  • National Research Foundation of Korea
  • Korean Government [Ministry of Science and ICT (MSIT)], South Korea
  • MSIT through the Information Technology Research Center (ITRC) Support Program
  • Artificial Intelligence Convergence Innovation Human Resources Development
  • Institute for Information and Communications Technology Planning and Evaluation

Zitieren

APA

Lee, S., & Jang, H. (2025). BiPruneFL: Computation and Communication Efficient Federated Learning With Binary Quantization and Pruning. IEEE Access, 13, 42441-42456. https://doi.org/10.1109/access.2025.3547627

Vancouver

Lee S, Jang H. BiPruneFL: Computation and Communication Efficient Federated Learning With Binary Quantization and Pruning. IEEE Access. 2025;13:42441-42456. doi:10.1109/access.2025.3547627

BibTeX
@article{Lee2025,
  author = {Lee, Sangmin and Jang, Hyeryung},
  title = {BiPruneFL: Computation and Communication Efficient Federated Learning With Binary Quantization and Pruning},
  journal = {IEEE Access},
  year = {2025},
  volume = {13},
  pages = {42441--42456},
  doi = {10.1109/access.2025.3547627}
}
Kostenlos starten →