Semi-Federated Learning: An Integrated Framework for Pervasive Intelligence in 6G Networks

Jingheng Zheng, Wanli Ni, Hui Tian, Deniz Gunduz, Tony Q.S. Quek

研究成果: Conference contribution

5 引文 斯高帕斯(Scopus)

摘要

In cellular-based federated learning (FL), the base station (BS) is only used to aggregate parameters, which incurs a waste of computing resources at the BS. In this paper, a novel semi-federated learning (SemiFL) framework is proposed to break this bottleneck, where local devices simultaneously send their gradient updates and training samples to the BS for global model computation. To capture the performance of SemiFL over wireless networks, a closed-form convergence upper bound of SemiFL is derived. Then, a non-convex problem is formulated to improve the convergence behavior of SemiFL, subject to the transmit power, communication latency, and computation distortion. To solve this intractable problem, a two-stage algorithm is proposed by controlling the transmit power and receive beamformers. Numerical experiments validate that the proposed SemiFL framework can effectively improve accuracy and accelerate convergence as compared to conventional FL.

原文English
主出版物標題INFOCOM WKSHPS 2022 - IEEE Conference on Computer Communications Workshops
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781665409261
DOIs
出版狀態Published - 2022
事件2022 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2022 - Virtual, Online, United States
持續時間: 2022 5月 22022 5月 5

出版系列

名字INFOCOM WKSHPS 2022 - IEEE Conference on Computer Communications Workshops

Conference

Conference2022 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2022
國家/地區United States
城市Virtual, Online
期間22-05-0222-05-05

All Science Journal Classification (ASJC) codes

  • 人工智慧
  • 電腦網路與通信
  • 資訊系統
  • 資訊系統與管理
  • 安全、風險、可靠性和品質

指紋

深入研究「Semi-Federated Learning: An Integrated Framework for Pervasive Intelligence in 6G Networks」主題。共同形成了獨特的指紋。

引用此