Föderiertes Lernverfahren und System zur Reduzierung des Domänenversatzes zwischen Clients

Details

Veröffentlichungs-Nr.

EP4764959

Anmeldetag

9. Dezember 2025

Veröffentlichung

24. Juni 2026

Rechtsraum

EP

IPC

G06N3/09, G06N3/098

Abstract

Disclosed are a federated learning method and system that can reduce domain skew between clients. The federated learning system according to an embodiment of the present disclosure includes a plurality of clients and a server, and each client is configured to input local data into a feature extractor to extract a feature vector, input the feature vector into a classifier to perform classification for a class of the local data, and train a local model, which includes the feature extractor and the classifier, using a first loss function based on a difference between an output value of the classifier and a preset correct value and a second loss function for contrastive learning between the feature vector and the generalized prototype of each class.

Anmelder

Firma

UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY

Land

🇰🇷 Südkorea

Fachgebiete