Personalized federated learning framework based on similarity-sense and selective communication protocols

With the advancement of edge computing and wearable technologies， a notable increase in the deployment of deep neural networks （DNNs） on endpoint devices has been observed.A personalized federated learning framework named Similarity-Sense Selective Knowledge Distillation （TSKD） is proposed to addres...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	LI Yan, ZHUANG Meng-Yu
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	Editorial Department of Journal of Sichuan University (Natural Science Edition) 2025-03-01
Schriftenreihe:	四川大学学报. 自然科学版
Schlagworte:	Federated learning Personalized predictive analytics Knowledge distillation Data heterogeneity Heterogeneity issues
Online-Zugang:	http://science.scu.edu.cn/thesisDetails#10.19907/j.0490-6756.240229
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!