Paper published in a journal (Scientific congresses, symposiums and conference proceedings)
Sparsification and Optimization for Energy-Efficient Federated Learning in Wireless Edge Networks
Lei, Lei; Yuan, Yaxiong; Yang, Yang et al.
2022In IEEE
Peer reviewed


Full Text
a513-lei final.pdf
Publisher postprint (253.56 kB)

All documents in ORBilu are protected by a user license.

Send to


Abstract :
[en] Federated Learning (FL), as an effective decentral- ized approach, has attracted considerable attention in privacy- preserving applications for wireless edge networks. In practice, edge devices are typically limited by energy, memory, and computation capabilities. In addition, the communications be- tween the central server and edge devices are with constrained resources, e.g., power or bandwidth. In this paper, we propose a joint sparsification and optimization scheme to reduce the energy consumption in local training and data transmission. On the one hand, we introduce sparsification, leading to a large number of zero weights in sparse neural networks, to alleviate devices’ computational burden and mitigate the data volume to be uploaded. To handle the non-smoothness incurred by sparsification, we develop an enhanced stochastic gradient descent algorithm to improve the learning performance. On the other hand, we optimize power, bandwidth, and learning parameters to avoid communication congestion and enable an energy-efficient transmission between the central server and edge devices. By collaboratively deploying the above two components, the numerical results show that the overall energy consumption in FL can be significantly reduced, compared to benchmark FL with fully-connected neural networks.
Disciplines :
Computer science
Author, co-author :
Lei, Lei
Yuan, Yaxiong
Yang, Yang
Luo, Yu
Pu, Lina
Chatzinotas, Symeon  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom
External co-authors :
Language :
Title :
Sparsification and Optimization for Energy-Efficient Federated Learning in Wireless Edge Networks
Publication date :
Event name :
2022 IEEE Global Communications Conference (GLOBECOM)
Event date :
4 to 8 December 2022
Audience :
Journal title :
Peer reviewed :
Peer reviewed
Focus Area :
Computational Sciences
Available on ORBilu :
since 19 December 2022


Number of views
38 (1 by Unilu)
Number of downloads
117 (2 by Unilu)

Scopus citations®
Scopus citations®
without self-citations
WoS citations


Similar publications

Contact ORBilu