Federal learning method and device, computer equipment and storage medium

The invention discloses a federal learning method and apparatus, a computer device and a storage medium. The method comprises the steps of obtaining a global model of a server and an initialization parameter of the global model; sending the global model and the initialization parameters to a plurali...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: LUO WEIJIE, CHEN YONGHONG, XIE CHONG, LAN PENG, CHEN KESHU, ZHAO YUSHAN
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention discloses a federal learning method and apparatus, a computer device and a storage medium. The method comprises the steps of obtaining a global model of a server and an initialization parameter of the global model; sending the global model and the initialization parameters to a plurality of clients participating in federal training; in the current iteration round stage of the client side, training data of the client side are obtained, multiple times of training are carried out on the global model and the initialization parameters according to the training data, trained local model parameters are determined by calculating the cross entropy loss of the model and model distillation, and a local model of the client side is obtained; sending the local model parameters of the client to a server, and obtaining initialization parameters of a next iteration round generated after aggregation of the server; and sending the initialization parameter of the next iteration round to the client as the initializa