EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Efficient Federated Learning Method FedLayerPrune Based on Layer Adaptive Pruning

Wenlong He, Hui Cao, Jisai Zhang, Decao Yang

Electronics · 02.03.2026 · 15 (5) · 1049

DOI: 10.3390/electronics15051049 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 02.03.2026. Verfasst von Wenlong He und 3 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As a privacy-preserving distributed machine learning paradigm, federated learning (FL) faces serious communication bottlenecks in practical deployment. In this paper, we propose FedLayerPrune, a communication-efficient federated learning method that integrates three synergistic components: (i) a layer-adaptive pruning strategy that dynamically allocates pruning rates based on layer sensitivity and network depth; (ii) a heterogeneity-aware aggregation mechanism that combines sample-size weighted averaging with mask consensus voting to enhance robustness under non-IID data distributions; and (iii) a dynamic pruning rate scheduler that progressively increases compression intensity across training rounds. Unlike existing approaches that apply uniform pruning or consider these techniques in isolation, FedLayerPrune achieves a principled coordination among layer-wise importance evaluation, temporal pruning scheduling, and heterogeneous model aggregation. Extensive experiments on CIFAR-10, MNIST, and Fashion-MNIST demonstrate that FedLayerPrune reduces communication costs by up to 68.3% compared with standard FedAvg, while maintaining model accuracy within a 2% margin. Moreover, our method exhibits stronger robustness and faster convergence under severe non-IID data distributions. These results suggest that FedLayerPrune provides a practical and effective solution for deploying federated learning in resource-constrained edge computing environments.

Zitieren

APA

He, W., Cao, H., Zhang, J., & Yang, D. (2026). Efficient Federated Learning Method FedLayerPrune Based on Layer Adaptive Pruning. Electronics, 15(5), 1049. https://doi.org/10.3390/electronics15051049

Vancouver

He W, Cao H, Zhang J, Yang D. Efficient Federated Learning Method FedLayerPrune Based on Layer Adaptive Pruning. Electronics. 2026;15(5):1049. doi:10.3390/electronics15051049

BibTeX
@article{He2026,
  author = {He, Wenlong and Cao, Hui and Zhang, Jisai and Yang, Decao},
  title = {Efficient Federated Learning Method FedLayerPrune Based on Layer Adaptive Pruning},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {5},
  pages = {1049},
  doi = {10.3390/electronics15051049}
}
Kostenlos starten →