Efficiency measurement of FL algorithms for image classification
Department of Computer Science & Engineering, American International University-Bangladesh, Khilkhet, Dhaka 1229, Bangladesh.
Research Article
GSC Advanced Research and Reviews, 2024, 18(03), 356–366.
Article DOI: 10.30574/gscarr.2024.18.3.0110
Publication history:
Received on 02 February 2024; revised on 16 March 2024; accepted on 19 March 2024
Abstract:
Federated Learning (FL) has emerged as a promising approach to collaborative machine learning without the need to share raw data. It enables decentralized model updates while preserving the privacy of each device and reducing the communication overhead. This experiment evaluates the effectiveness of the personalized FL algorithms, namely FedAvg, APPLE, FedBABU and FedProto, in a decentralized setting, with a particular focus on the Fashion MNIST dataset, which is characterized by a non-ideal data distribution. The objective is to identify which algorithm performs optimally in image classification tasks. The experimental results show that both FedProto and APPLE have nearly equivalent and better performance compared to FedBABU and FedAvg. Interestingly, increasing the number of uploads in FedBABU leads to similar results to APPLE and FedProto. However, under limited upload conditions, FedBABU performs similarly to FedAvg. These results provide valuable insights into the differential performance of personalized FL algorithms in non-id data scenarios and provide guidance for their application in distributed environments, especially in sensitive domains such as medical, military and confidential image analysis tasks where privacy and communication efficiency are paramount concerns.
Keywords:
Federated learning (FL); Data privacy; Model personalization; Image classification
Full text article in PDF:
Copyright information:
Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0
