DP-FedDRC: differentially private personalized federated learning to alleviate dimension collapse

Federated learning faces dual challenges of data heterogeneity and privacy leakage in distributed privacy-preserving scenarios. Personalized federated learning mitigates data distribution discrepancies by constraining local model update directions, while differential privacy provides rigorous privac...

Descripció completa

Dades bibliogràfiques

Autors principals:	Wang Minli, Zhang Yuhao, Hu Changhui
Format:	Artigo
Idioma:	Inglês
Publicat:	POSTS&TELECOM PRESS Co., LTD 2026-02-01
Col·lecció:	网络与信息安全学报
Matèries:	federated learning differential privacy dimension collapse non-IID data feature decorrelation
Accés en línia:	http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2026008
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!