FedCoSim: an efficient federated learning with cosine similarity on data heterogeneity
The Journal of Supercomputing · 03.07.2026 · 82 (10)
DOI: 10.1007/s11227-026-08682-4 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of Supercomputing, online erschienen am 03.07.2026. Verfasst von Qiantao Yang und 3 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Central Plains Talent Program.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- National Natural Science Foundation of China
- Central Plains Talent Program
Zitieren
APA
Yang, Q., Chen, L., Du, X., & Wu, X. (2026). FedCoSim: an efficient federated learning with cosine similarity on data heterogeneity. The Journal of Supercomputing, 82(10). https://doi.org/10.1007/s11227-026-08682-4
Vancouver
Yang Q, Chen L, Du X, Wu X. FedCoSim: an efficient federated learning with cosine similarity on data heterogeneity. The Journal of Supercomputing. 2026;82(10). doi:10.1007/s11227-026-08682-4
BibTeX
@article{Yang2026,
author = {Yang, Qiantao and Chen, Liquan and Du, Xuehui and Wu, Xiangyu},
title = {FedCoSim: an efficient federated learning with cosine similarity on data heterogeneity},
journal = {The Journal of Supercomputing},
year = {2026},
volume = {82},
number = {10},
doi = {10.1007/s11227-026-08682-4}
}
EUVIMED