Dmaf: data-model anti-forgetting for federated incremental learning

Federated Learning has received much attention due to its data privacy benefits, but most existing approaches assume that client classes are fixed. Clients may remove old classes and add new ones, leading to catastrophic forgetting of the model. Existing methods have limitations, such as requiring a...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Cluster computing 2025-02, Vol.28 (1), p.30, Article 30
Hauptverfasser:	Zhu, Kongshang, Xu, Jiuyun, Zhou, Liang, Li, Xiaowen, Zhao, Yingzhi, Xu, Xiangrui, Li, Shibao
Format:	Artikel
Sprache:	eng
Schlagworte:	Clients Computer Communication Networks Computer Science Effectiveness Federated learning Geography Knowledge Machine learning Operating Systems Privacy Processor Architectures Synthetic data Teachers Trends
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!