COMPARATIVE ANALYSIS OF FEDERATED MACHINE LEARNING ALGORITHMS - Comparative study of FedAdam, FedYogi and FedSparse

Aug 2, 2026

Federated machine learning enables accurate model training while keeping private data on end devices, avoiding direct data sharing among clients. The approach lowers network traffic and communication costs through iterative rounds of local training with model aggregation, supporting privacy by design. The paper compares FedAdam, FedYogi and FedSparse and highlights that FedAvg is foundational to many federated algorithms. Experiments use Flower and Kaggle platforms, and application considerations include security, client selection, aggregation quality, and platform choices for risk-sensitive domains.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Introduction

Federated machine learning concept and workflow

Algorithm comparison: FedAdam, FedYogi, FedSparse (and FedAvg)

Experimental setup and evaluation platforms

Key aspects: privacy, security, client selection, communication cost, aggregation platform

Historical background and research trends

DOI: 10. 37943/17BVCN7579 © Gulnara Bektemyssova, Gulnaz Bakirova 57 DOI: 10.37943/17BVCN7579 Gulnara Bektemyssova Candidate of Technical Sciences, Professor of the Department of Computer Engineering [g.bektemisova@iitu.edu.kz](g.bektemisova@iitu.edu.kz), [orcid.org/0000-0002-0850-0558](orcid.org/0000-0002-0850-0558)[ ](orcid.org/0000-0002-0850-0558)International Information Technology University, Kazakhstan Gulnaz Bakirova PhD candidate of the Department of Computer Engineering [g.bakirova@iitu.edu.kz](g.bakirova@iitu.edu.kz), [orcid.org/0009-0006-5643-2349](orcid.org/0009-0006-5643-2349)[ ](orcid.org/0009-0006-5643-2349)International Information Technology University, Kazakhstan COMPARATIVE ANALYSIS OF FEDERATED MACHINE LEARNING ALGORITHMS Abstract: In this paper, the authors propose a new machine learning paradigm, federated machine learning. This method produces accurate predictions without revealing private data. It requires less network traffic, reduces communication costs and enables private learning from device to device. Federated machine learning helps to build models and further the models are moved to the device. Applications are particularly prevalent in healthcare, finance, retail, etc. , as regulations make it difficult to share sensitive information. Note that this method creates an opportunity to build models with huge amounts of data by combining multiple databases and devices. There are many algorithms available in this area of machine learning and new ones are constantly being created. Our paper presents a comparative analysis of algorithms: FedAdam, FedYogi and FedSparse. But we need to keep in mind that FedAvg is at the core of many federated machine learning algorithms. Data testing was conducted using the Flower and Kaggle platforms with the above algorithms. Federated machine learning technology is usable in smartphones and other devices where it can create accurate predictions without revealing raw personal data. In organizations, it can reduce network load and enable private learning between devices. Federated machine learning can help develop models for the Internet of Things that adapt to changes in the system while protecting user privacy. And it is also used to develop an AI model to meet the risk requirements of leaking client’s personal data. The main aspects to consider are privacy and security of the data, the choice of the client to whom the algorithm itself will be directed to process the data, communication costs as well as its quality, and the platform for model aggregation. Keywords: federated learning; FedAvg; FedAdam; FedYogi; FedSparse; loss; accuracy. Introduction The usage of federated Learning helps clients to train a global model without sharing their data. It is a new machine learning paradigm that works with decentralized data from multiple clients to train a global model [1]. These days,“big” data is collected by distributed networks made up of gadgets, cars, and cellphones. Local data storage is getting more and more appealing due to the devices is rising processing capability and worries about the transmission of sensitive information. Clients in federated learning independently gather local data according to their own device [2]. Copyright © 2024, Authors. This is an open access article under the Creative Commons CC BY-NC-ND license 58 Scientific Journal of Astana IT University ISSN (P): 2707-9031 ISSN (E): 2707-904X VolUmE 17, mArch 2024 The main idea is sending the model to the device and the data stays on the device. This method guarantees that the learning process of the model works right on the end devices. So, you can train the model on datasets located in different places without having to interact with the actual data, to make the universal global model with no necessity to centralize the local data. Individualized data stays localized, minimizing the potential risk of client data exposure [3]. Put differently, the training of a

FAQs

What problem does federated machine learning address?

It allows clients to train a global model without sharing their raw private data, keeping learning on end devices while still improving prediction quality.

How does the federated learning process work at a high level?

A global model is sent to local devices or servers, clients train local models on local datasets, and the system iteratively aggregates updates to refine global performance.

Which algorithms are compared in the paper?

The paper presents a comparative analysis of FedAdam, FedYogi, and FedSparse, while noting that FedAvg is at the core of many federated machine learning algorithms.

Aug 2, 2026

Upload by Emma Wilson