Training efficiency optimization algorithm of wireless federated learning based on processor performance and network condition awareness

With the explosive growth of smart mobile devices in wireless networks, the increasing computational power of mobile chips and the growing concern for personal privacy, a decentralized deep learning framework at the mobile terminal layer has emerged called federated learning (FL) to enhance user exp...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:EURASIP journal on advances in signal processing Jg. 2024; H. 1; S. 98 - 28
Hauptverfasser: Pang, Guohao, Zhu, Xiaorong
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Cham Springer International Publishing 01.12.2024
Springer
Springer Nature B.V
SpringerOpen
Schlagworte:
Algorithms
Analysis
Communications networks
Decoupling
Deep learning
Efficiency
Energy consumption
Engineering
Federated learning
Machine learning
Mathematical optimization
Microprocessors
Mobile devices
Network latency
Optimization
Optimization algorithms
Parallel and distributed algorithms
Quantum Information Technology
Resource allocation
Scheduling
Scheduling policies
Signal processing
Signal,Image and Speech Processing
Spintronics
Telecommunication systems
User experience
Wireless communication
Wireless communications
Wireless networks
Florida
Wireless communication
Scheduling policies
Federated learning
Parallel and distributed algorithms
Resource allocation
ISSN:1687-6180, 1687-6172, 1687-6180
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:With the explosive growth of smart mobile devices in wireless networks, the increasing computational power of mobile chips and the growing concern for personal privacy, a decentralized deep learning framework at the mobile terminal layer has emerged called federated learning (FL) to enhance user experience. This paper studies the training efficiency optimization problem of wireless FL that jointly considers processor performance, channel conditions and terminals’ power in a non-independent identically distribution (non-IID) scenario. And, the training efficiency optimization problem is mathematically modeled and then decomposed into several sub-problems based on the independence and decoupling of the variables involved. To enhance the training efficiency of wireless FL, a comprehensive scheduling strategy encompassing computational and communication aspects is proposed. Simulation results show that the proposed scheduling strategy for wireless FL achieves superior learning performance with reduced training latency.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1687-6180
1687-6172
1687-6180
DOI:10.1186/s13634-024-01192-6