FedRazor: Two-Stage Federated Unlearning via Representation Divergence and Gradient Conflict Trimming

Federated unlearning removes a client’s influence from a trained federated model without full retraining, which is required by data deletion regulations but remains difficult due to gradient coupling and recovery instability. Existing methods often rely on historical training records or suffer from...

Descripció completa

Dades bibliogràfiques

Autors principals:	Yanxin Hu, Xiaoman Liu, Yan Huang, Junjie Pang, Chao Cheng, Gang Liu
Format:	Artigo
Idioma:	Inglês
Publicat:	MDPI AG 2026-02-01
Col·lecció:	Information
Matèries:	federated unlearning federated learning client-level unlearning
Accés en línia:	https://www.mdpi.com/2078-2489/17/2/146
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!