Federated Edge Learning
Algorithms, Architectures and Trustworthiness
Springer
ISBN 978-3-031-96648-4
Standardpreis
Bibliografische Daten
Fachbuch
Buch. Hardcover
2025
4 s/w-Abbildungen, 35 Farbabbildungen.
In englischer Sprache
Umfang: xvi, 187 S.
Format (B x L): 15,5 x 23,5 cm
Verlag: Springer
ISBN: 978-3-031-96648-4
Weiterführende bibliografische Daten
Das Werk ist Teil der Reihe: Wireless Networks
Produktbeschreibung
The convergence rate, computation complexity and communication overhead of the federated zeroth/first/second-order algorithms over wireless networks are elaborated. From the networking architecture perspective, the authors illustrate how the critical challenges of FEEL can be addressed by exploiting different architectures and designing effective communication schemes. Specifically, the communication straggler issue of FEEL can be mitigated by reconfiguring the propagation environment. By utilizing reconfigurable intelligent and unmanned aerial vehicle, while over-the-air computation is utilized to support ultra-fast model aggregation for FEEL, by exploiting the waveform superposition property. Additionally, the multi-cell architecture presents a feasible solution for collaborative FEEL training among multiple cells. Finally, the authors discuss the challenges of FEEL from the privacy and security perspective, followed by presenting effective communication schemes that can achieve differentially private model aggregation and Byzantine-resilient model aggregation to achieve trustworthy FEEL.
This book is designed for advanced-level students majoring in computer science and electrical engineering as a secondary text. Researchers and professionals working in wireless communications will also find this book useful as a reference.
Autorinnen und Autoren
Produktsicherheit
Hersteller
Springer Nature Customer Service Center GmbH
ProductSafety@springernature.com