An Efficient Federated Learning Framework for Training Semantic Communication Systems

Semantic communication has emerged as a pillar for the next generation of communication systems due to its capabilities in alleviating data redundancy. Most semantic communication systems are built upon advanced deep learning models whose training performance heavily relies on data availability. Exi...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on vehicular technology Ročník 73; číslo 10; s. 15872 - 15877
Hlavní autori: Nguyen, Loc X., Le, Huy Q., Tun, Ye Lin, Aung, Pyae Sone, Tun, Yan Kyaw, Han, Zhu, Hong, Choong Seon
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 01.10.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Communication
Communication overhead
Communications systems
Communications traffic
Data models
Decoding
deep joint source-channel coding (JSCC). federated learning
Deep learning
Feature extraction
Federated learning
Privacy
Redundancy
semantic communication
Semantics
Training
Transformers
ISSN:0018-9545, 1939-9359
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Semantic communication has emerged as a pillar for the next generation of communication systems due to its capabilities in alleviating data redundancy. Most semantic communication systems are built upon advanced deep learning models whose training performance heavily relies on data availability. Existing studies often make unrealistic assumptions of a readily accessible data source, where in practice, data is mainly created on the client side. This circumstance limits the transmission of data due to privacy concerns, which is necessary for conventional centralized training schemes. To address this challenge, we explore semantic communication in a federated learning (FL) setting, which can harness the data of clients without compromising their privacy. Additionally, we design our system to lower the communication overhead by reducing the quantity of information delivered in each FL training round. This not only allows us to save significant bandwidth for resource-constrained devices but also reduces overall network traffic. Finally, we introduce a mechanism to aggregate the global model based on the client's performance, which we have referred to as FedLol. Extensive simulation results demonstrate the effectiveness of our proposed technique compared to baseline methods.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9545
1939-9359
DOI:10.1109/TVT.2024.3401140