Privacy-preserving federated learning framework with dynamic weight aggregation

There are two problems with the privacy-preserving federal learning framework under an unreliable central server.① A fixed weight, typically the size of each participant’s dataset, is used when aggregating distributed learning models on the central server.However, different participants have non-ind...

Cijeli opis

Bibliografski detalji

Glavni autori:	Zuobin YING, Yichen FANG, Yiwen ZHANG
Format:	Artigo
Jezik:	Inglês
Izdano:	POSTS&TELECOM PRESS Co., LTD 2022-10-01
Serija:	网络与信息安全学报
Teme:	federated learning differential privacy dynamic aggregation weight non-independent and identically distributed data
Online pristup:	http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2022069
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!