Semi-Asynchronous Model Design for Federated Learning in Mobile Edge Networks

Federated learning (FL) is a distributed machine learning (ML). Distributed clients train locally and exclusively need to upload the model parameters to learn the global model collaboratively under the coordination of the aggregation server. Although the privacy of the clients is protected, which re...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on vehicular technology Jg. 72; H. 12; S. 1 - 14
Hauptverfasser: Zhang, Jinfeng, Liu, Wei, He, Yejun, He, Zhou, Guizani, Mohsen
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 01.12.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Accuracy
Adaptation models
Algorithms
Clients
Communication
Convergence
deep deterministic policy gradient
Delays
Edge computing
Empirical analysis
Energy consumption
energy efficient
Federated learning
Heterogeneity
Machine learning
Mathematical models
Mobile computing
mobile edge networks
Optimization
Parameters
semi-asynchronous update model
Servers
Training
ISSN:0018-9545, 1939-9359
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Federated learning (FL) is a distributed machine learning (ML). Distributed clients train locally and exclusively need to upload the model parameters to learn the global model collaboratively under the coordination of the aggregation server. Although the privacy of the clients is protected, which requires multiple rounds of data upload between the clients and the server to ensure the accuracy of the global model. Inevitably, this results in latency and energy consumption issues due to limited communication resources. Therefore, mobile edge computing (MEC) has been proposed to solve communication delays and energy consumption in federated learning. In this paper, we first analyze how to select the gradient values that help the global model converge quickly and establish theoretical analysis about the relationship between the convergence rate and the gradient direction. To efficiently reduce the energy consumption of clients during training, on the premise of ensuring the local training accuracy and the convergence rate of the global model, we adopt the deep deterministic policy gradient (DDPG) algorithm, which adaptively allocates resources according to different clients' requests to minimize the energy consumption. To improve flexibility and scalability, we propose a new semi-asynchronous federated update model, which allows clients to aggregate asynchronously on the server, and accelerates the convergence rate of the global model. Empirical results show that the proposed Algorithm 1 not only accelerates the convergence speed of the global model, but also reduces the size of parameters that need to be uploaded. Besides, the proposed Algorithm 2 reduces the time difference caused by users heterogeneity. Eventually, semi-asynchronous update model is better than synchronous update model in communication time.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9545
1939-9359
DOI:10.1109/TVT.2023.3298787