EUVIMEDEUVIMED entdecken
Crossref

A Graph Neural Network Learning Approach to Optimize RIS-Assisted Federated Learning

Zixin Wang, Yong Zhou, Yinan Zou, Qiaochu An, Yuanming Shi, Mehdi Bennis

IEEE Transactions on Wireless Communications · 2023-09 · 22 (9) · 6092-6106

DOI: 10.1109/twc.2023.3239400 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Wireless Communications, 2023-09. Verfasst von Zixin Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 70-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shanghai, Shanghai Rising-Star Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Over-the-air federated learning (FL) is a promising privacy-preserving edge artificial intelligence paradigm, where over-the-air computation enables spectral-efficient model aggregation by achieving simultaneous communication and aggregation. However, due to limited transmit power, the performance of over-the-air FL is limited by the device with the worst channel condition toward the edge server. In this paper, we leverage reconfigurable intelligent surface (RIS) to mitigate the communication bottleneck of over-the-air FL and explicitly characterize the corresponding convergence upper bound. The convergence analysis illustrates the detrimental impact of the accumulated aggregation error over all rounds and inspires us to formulate a time-average transmission distortion minimization problem by jointly optimizing the transceiver and RIS phase-shifts. To reduce the computation complexity and enhance the model aggregation accuracy, we develop a graph neural network (GNN) based learning algorithm to directly map channel coefficients to the optimized network parameters. By exploiting permutation equivalence and invariance properties of graphs, the parameter dimension of the proposed algorithm is independent of the number of edge devices, which reduces the computational complexity and improves the algorithmic scalability. Simulations show that the proposed algorithm speeds up the computation by three orders of magnitude compared to the baselines, while achieving performance superiority and algorithmic robustness.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Shanghai
  • Shanghai Rising-Star Program

Zitieren

APA

Wang, Z., Zhou, Y., Zou, Y., An, Q., Shi, Y., & Bennis, M. (2023). A Graph Neural Network Learning Approach to Optimize RIS-Assisted Federated Learning. IEEE Transactions on Wireless Communications, 22(9), 6092-6106. https://doi.org/10.1109/twc.2023.3239400

Vancouver

Wang Z, Zhou Y, Zou Y, An Q, Shi Y, Bennis M. A Graph Neural Network Learning Approach to Optimize RIS-Assisted Federated Learning. IEEE Transactions on Wireless Communications. 2023;22(9):6092-6106. doi:10.1109/twc.2023.3239400

BibTeX
@article{Wang2023,
  author = {Wang, Zixin and Zhou, Yong and Zou, Yinan and An, Qiaochu and Shi, Yuanming and Bennis, Mehdi},
  title = {A Graph Neural Network Learning Approach to Optimize RIS-Assisted Federated Learning},
  journal = {IEEE Transactions on Wireless Communications},
  year = {2023},
  volume = {22},
  number = {9},
  pages = {6092--6106},
  doi = {10.1109/twc.2023.3239400}
}
Kostenlos starten →