Performance evaluation of cluster-based federated machine learning

Federated Learning (FL) is a collaborative training method for machine learning (ML) that aggregates model weights from multiple participants during the training phase. The learning phase of machine learning techniques is distributed, in which each participating device trains a model using its local...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neural computing & applications 2024-05, Vol.36 (14), p.7657-7668
Hauptverfasser: Sattar, Karim Asif, Baroudi, Uthman
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Federated Learning (FL) is a collaborative training method for machine learning (ML) that aggregates model weights from multiple participants during the training phase. The learning phase of machine learning techniques is distributed, in which each participating device trains a model using its local data set and sends model weights to a centralized node. The central node aggregates weights and sends the updated weights back to devices. The process continues until a specific threshold is reached such accuracy, response time. In this paper, we present a performance evaluation of FL in a clustering-based multi-hop network to simulate the effect of the dynamic environment on the accuracy of the global model. It is observed that a minimum number of participating nodes is required within a cluster to maintain a high level of global accuracy. A global threshold value needs to be defined to maintain high global accuracy and avoid degradation of model performance.
ISSN:0941-0643
1433-3058
DOI:10.1007/s00521-024-09487-3