EUVIMEDEUVIMED entdecken
Crossref

Wireless Federated Learning Over Resource-Constrained Networks: Digital Versus Analog Transmissions

Jiacheng Yao, Wei Xu, Zhaohui Yang, Xiaohu You, Mehdi Bennis, H. Vincent Poor

IEEE Transactions on Wireless Communications · 2024-10 · 23 (10) · 14020-14036

DOI: 10.1109/twc.2024.3407822 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Wireless Communications, 2024-10. Verfasst von Jiacheng Yao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 61-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To enable wireless federated learning (FL) in communication resource-constrained networks, two communication schemes, i.e., digital and analog ones, are effective solutions. In this paper, we quantitatively compare these two techniques, highlighting their essential differences as well as respectively suitable scenarios. We first examine both digital and analog transmission schemes, together with a unified and fair comparison framework under imbalanced device sampling, strict latency targets, and transmit power constraints. A universal convergence analysis under various imperfections is established for evaluating the performance of FL over wireless networks. These analytical results reveal that the fundamental difference between the digital and analog communications lies in whether communication and computation are jointly designed or not. The digital scheme decouples the communication design from FL computing tasks, making it difficult to support uplink transmission from massive devices with limited bandwidth and hence the performance is mainly communication-limited. In contrast, the analog communication allows over-the-air computation (AirComp) and achieves better spectrum utilization. However, the computation-oriented analog transmission reduces power efficiency, and its performance is sensitive to computation errors from imperfect channel state information (CSI). Furthermore, device sampling for both schemes are optimized and differences in sampling optimization are analyzed. Numerical results verify the theoretical analysis and affirm the superior performance of the sampling optimization.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Yao, J., Xu, W., Yang, Z., You, X., Bennis, M., & Poor, H. V. (2024). Wireless Federated Learning Over Resource-Constrained Networks: Digital Versus Analog Transmissions. IEEE Transactions on Wireless Communications, 23(10), 14020-14036. https://doi.org/10.1109/twc.2024.3407822

Vancouver

Yao J, Xu W, Yang Z, You X, Bennis M, Poor HV. Wireless Federated Learning Over Resource-Constrained Networks: Digital Versus Analog Transmissions. IEEE Transactions on Wireless Communications. 2024;23(10):14020-14036. doi:10.1109/twc.2024.3407822

BibTeX
@article{Yao2024,
  author = {Yao, Jiacheng and Xu, Wei and Yang, Zhaohui and You, Xiaohu and Bennis, Mehdi and Poor, H. Vincent},
  title = {Wireless Federated Learning Over Resource-Constrained Networks: Digital Versus Analog Transmissions},
  journal = {IEEE Transactions on Wireless Communications},
  year = {2024},
  volume = {23},
  number = {10},
  pages = {14020--14036},
  doi = {10.1109/twc.2024.3407822}
}
Kostenlos starten →