Original scientific paper

https://doi.org/10.24138/jcomss-2024-0091 C

KiFramework — A Federated Learning Platform with an Innovative Communication Protocol

Jakub Michalek orcid.org/0000-0001-5504-7533 ; Brno University of Technology, Brno, Czech Republic
Vaclav Oujezsky orcid.org/0000-0001-7629-6299 ; Brno University of Technology, Brno, Czech Republic
Vladislav Skorpil ; Brno University of Technology, Brno, Czech Republic

Abstract

This paper presents a newly developed framework for federated learning adapted to crisis management applications on the Android platform. This framework focuses on solving client communication problems during the federated learning process. KiFramework introduces an innovative communication protocol and framework that enhances data exchange reliability and supports efficient collaboration in multi-server environments, addressing key challenges in traditional centralized server architectures. Our research provides a comprehensive solution to optimize communication and ensure seamless collaboration among multiple servers, improving applications’ efficiency using federated learning.

Keywords

Android; communication protocol; federated learning; framework; Machine Learning

Hrčak ID:

326641

URI

https://hrcak.srce.hr/326641

Publication date:

31.12.2024.

Visits: 477 *