Proceedings of the Annual Conference of JSAI
Online ISSN : 2758-7347
38th (2024)
Session ID : 3P5-OS-17a-05
Conference information

Quantification of Data Uniqueness by Federated Learning with Autonomous Client Models
*Shunsuke KAWANOYoshitaka YAMAMOTODaisuke KAJI
Author information
CONFERENCE PROCEEDINGS FREE ACCESS

Details
Abstract

Recently, Federated Learning (FL) has been attracting attention as a method for learning from distributed data. While FL has advantages such as privacy protection and reduced data traffic, it is difficult to characterize the non-i.i.d data of each client since data collection is not performed on the server side. In this study, we quantify the uniqueness of the data using FL with autonomous client models, which deals with a general model corresponding to all data constructed by the server side and a personalized model for each client data. The validity of the proposed method is assessed in terms of model performance and data feature extraction.

Content from these authors
© 2024 The Japanese Society for Artificial Intelligence
Previous article Next article
feedback
Top