RIS-Assisted Federated Learning Algorithm Based on Device Selection and Weighted Averaging

Yujun Cai; Shufeng Li; Junwei Zhang; Deyou Zhang

doi:10.1109/VTC2024-Spring62846.2024.10683452

RIS-Assisted Federated Learning Algorithm Based on Device Selection and Weighted Averaging

Yujun Cai
, Shufeng Li
, Junwei Zhang
, Deyou Zhang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

To protect user privacy and improve the transmitting environment of wireless communication, federated learning (FL) and reconfigurable intelligent surface (RIS) are proposed as promising technologies for future communication. Meanwhile, studies have proved that the combination of FL and RIS guarantees better performance for system models. However, the combined model still has problems such as high communication overhead and slow convergence speed. Therefore, in this paper, we proposed a channel quality based device selection and weighted averaging algorithm in a RIS-assisted federated learning model. Simulation results proved that the proposed algorithm outperforms the classic federated averaging (FedAvg) algorithm in convergence speed, test accuracy, and training loss.

Original language	English
Title of host publication	2024 IEEE 99th Vehicular Technology Conference, VTC2024-Spring 2024 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350387414
DOIs	https://doi.org/10.1109/VTC2024-Spring62846.2024.10683452
State	Published - 2024
Externally published	Yes
Event	99th IEEE Vehicular Technology Conference, VTC2024-Spring 2024 - Singapore, Singapore Duration: 24 Jun 2024 → 27 Jun 2024

Publication series

Name	IEEE Vehicular Technology Conference
ISSN (Print)	1550-2252

Conference

Conference	99th IEEE Vehicular Technology Conference, VTC2024-Spring 2024
Country/Territory	Singapore
City	Singapore
Period	24/06/24 → 27/06/24

Keywords

device selection
federated learning
reconfigurable intelligent surface
weighted averaging

Access to Document

10.1109/VTC2024-Spring62846.2024.10683452

Cite this

Cai, Y., Li, S., Zhang, J., & Zhang, D. (2024). RIS-Assisted Federated Learning Algorithm Based on Device Selection and Weighted Averaging. In 2024 IEEE 99th Vehicular Technology Conference, VTC2024-Spring 2024 - Proceedings (IEEE Vehicular Technology Conference). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VTC2024-Spring62846.2024.10683452

@inproceedings{3b1634832fc248f3a305e00ee9662b1a,

title = "RIS-Assisted Federated Learning Algorithm Based on Device Selection and Weighted Averaging",

abstract = "To protect user privacy and improve the transmitting environment of wireless communication, federated learning (FL) and reconfigurable intelligent surface (RIS) are proposed as promising technologies for future communication. Meanwhile, studies have proved that the combination of FL and RIS guarantees better performance for system models. However, the combined model still has problems such as high communication overhead and slow convergence speed. Therefore, in this paper, we proposed a channel quality based device selection and weighted averaging algorithm in a RIS-assisted federated learning model. Simulation results proved that the proposed algorithm outperforms the classic federated averaging (FedAvg) algorithm in convergence speed, test accuracy, and training loss.",

keywords = "device selection, federated learning, reconfigurable intelligent surface, weighted averaging",

author = "Yujun Cai and Shufeng Li and Junwei Zhang and Deyou Zhang",

note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 99th IEEE Vehicular Technology Conference, VTC2024-Spring 2024 ; Conference date: 24-06-2024 Through 27-06-2024",

year = "2024",

doi = "10.1109/VTC2024-Spring62846.2024.10683452",

language = "英语",

series = "IEEE Vehicular Technology Conference",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2024 IEEE 99th Vehicular Technology Conference, VTC2024-Spring 2024 - Proceedings",

address = "美国",

}

Cai, Y, Li, S, Zhang, J & Zhang, D 2024, RIS-Assisted Federated Learning Algorithm Based on Device Selection and Weighted Averaging. in 2024 IEEE 99th Vehicular Technology Conference, VTC2024-Spring 2024 - Proceedings. IEEE Vehicular Technology Conference, Institute of Electrical and Electronics Engineers Inc., 99th IEEE Vehicular Technology Conference, VTC2024-Spring 2024, Singapore, Singapore, 24/06/24. https://doi.org/10.1109/VTC2024-Spring62846.2024.10683452

RIS-Assisted Federated Learning Algorithm Based on Device Selection and Weighted Averaging. / Cai, Yujun; Li, Shufeng; Zhang, Junwei et al.
2024 IEEE 99th Vehicular Technology Conference, VTC2024-Spring 2024 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2024. (IEEE Vehicular Technology Conference).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - RIS-Assisted Federated Learning Algorithm Based on Device Selection and Weighted Averaging

AU - Cai, Yujun

AU - Li, Shufeng

AU - Zhang, Junwei

AU - Zhang, Deyou

PY - 2024

Y1 - 2024

N2 - To protect user privacy and improve the transmitting environment of wireless communication, federated learning (FL) and reconfigurable intelligent surface (RIS) are proposed as promising technologies for future communication. Meanwhile, studies have proved that the combination of FL and RIS guarantees better performance for system models. However, the combined model still has problems such as high communication overhead and slow convergence speed. Therefore, in this paper, we proposed a channel quality based device selection and weighted averaging algorithm in a RIS-assisted federated learning model. Simulation results proved that the proposed algorithm outperforms the classic federated averaging (FedAvg) algorithm in convergence speed, test accuracy, and training loss.

AB - To protect user privacy and improve the transmitting environment of wireless communication, federated learning (FL) and reconfigurable intelligent surface (RIS) are proposed as promising technologies for future communication. Meanwhile, studies have proved that the combination of FL and RIS guarantees better performance for system models. However, the combined model still has problems such as high communication overhead and slow convergence speed. Therefore, in this paper, we proposed a channel quality based device selection and weighted averaging algorithm in a RIS-assisted federated learning model. Simulation results proved that the proposed algorithm outperforms the classic federated averaging (FedAvg) algorithm in convergence speed, test accuracy, and training loss.

KW - device selection

KW - federated learning

KW - reconfigurable intelligent surface

KW - weighted averaging

UR - https://www.scopus.com/pages/publications/85206130143

U2 - 10.1109/VTC2024-Spring62846.2024.10683452

DO - 10.1109/VTC2024-Spring62846.2024.10683452

M3 - 会议稿件

AN - SCOPUS:85206130143

T3 - IEEE Vehicular Technology Conference

BT - 2024 IEEE 99th Vehicular Technology Conference, VTC2024-Spring 2024 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 99th IEEE Vehicular Technology Conference, VTC2024-Spring 2024

Y2 - 24 June 2024 through 27 June 2024

ER -

RIS-Assisted Federated Learning Algorithm Based on Device Selection and Weighted Averaging

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this