EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FedDCS: Semi-Asynchronous Federated Learning Optimization Based on Dynamic Client Selection

Ruilin Liu, Lili Zhang

Mathematics · 27.02.2026 · 14 (5) · 803

DOI: 10.3390/math14050803 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 27.02.2026. Verfasst von Ruilin Liu und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: International Partnership Program of the Chinese Academy of Sciences “Global Open Science Cloud Initiative”, National Natural Science Foundation of China “Research on the Measurement of Scientific Data Reusability through An Extended Citation Framework”, CNIC.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated Learning (FL) represents a promising paradigm for collaborative model training across numerous devices, preserving data locality and offering potential privacy benefits for industries such as finance, healthcare, and Internet of Things (IoT). Nonetheless, real-world deployments of FL encounter challenges arising from dynamic and diverse environments, which adversely affect training speed and model convergence. To address these issues, this paper introduces FedDCS, an adaptive federated learning framework that effectively manages resources during training through two primary innovations. First, it establishes a reliable method for predicting client training durations, estimating completion times while filtering noise and detecting performance variations. Second, it implements a two-stage adaptive waiting strategy that dynamically determines the optimal timing and selection of client batches for aggregation, thereby balancing collection efficiency with model accuracy. This approach optimizes the trade-off between efficiency and accuracy in heterogeneous settings. Extensive evaluations on datasets such as Fashion-MNIST and CIFAR-10/100, incorporating simulated device and data heterogeneity, demonstrate that FedDCS consistently achieves superior time efficiency and higher global model accuracy compared to state-of-the-art (e.g., synchronous, asynchronous, and semi-asynchronous) baselines. Its robustness and versatility render it effective across various complex and heterogeneous environments.

Förderung

  • International Partnership Program of the Chinese Academy of Sciences “Global Open Science Cloud Initiative”
  • National Natural Science Foundation of China “Research on the Measurement of Scientific Data Reusability through An Extended Citation Framework”
  • CNIC

Zitieren

APA

Liu, R., & Zhang, L. (2026). FedDCS: Semi-Asynchronous Federated Learning Optimization Based on Dynamic Client Selection. Mathematics, 14(5), 803. https://doi.org/10.3390/math14050803

Vancouver

Liu R, Zhang L. FedDCS: Semi-Asynchronous Federated Learning Optimization Based on Dynamic Client Selection. Mathematics. 2026;14(5):803. doi:10.3390/math14050803

BibTeX
@article{Liu2026,
  author = {Liu, Ruilin and Zhang, Lili},
  title = {FedDCS: Semi-Asynchronous Federated Learning Optimization Based on Dynamic Client Selection},
  journal = {Mathematics},
  year = {2026},
  volume = {14},
  number = {5},
  pages = {803},
  doi = {10.3390/math14050803}
}
Kostenlos starten →