Model-Agnostic Personalized Federated Learning using Adaptive Client Selection

Thumbnail Image

Files

master_Dang_Phi_2025.pdf (2.18 MB)

URL

Journal Title

Journal ISSN

Volume Title

School of Science | Master's thesis
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.

Authors

Date

2024-12-31

Department

Major/Subject

Machine Learning, Data Science and Artificial Intelligence

Mcode

Degree programme

Master's Programme in Computer, Communication and Information Sciences

Language

en

Pages

61

Series

Abstract

Personalized Federated Learning (pFL) addresses the challenges of heterogeneous and decentralized data by enabling client-specific model training without sharing raw data. This thesis introduces a novel method for model-agnostic pFL that leverages adaptive client selection to improve the personalization of client models. By assuming cluster-based distributions of local datasets, the proposed algorithms iteratively select and incorporate the most beneficial candidate datasets to optimize each client's model. Two main methodologies are presented: one tailored for parametric models using gradient-based updates and another designed for non-parametric models using a generalized optimization approach. Experimental evaluations on synthetic datasets and the Fashion-MNIST benchmark demonstrate significant improvements in both classification and regression metrics, including accuracy and mean squared error, when compared to baseline models and established methods. The results highlight the potential of adaptive collaboration in achieving robust personalization while maintaining privacy.

Description

Supervisor

Jung, Alex

Keywords

machine learning, federated learning, personalization, gradient descent, non-parametric models, candidate selection

Other note

Citation

Permanent link to this item

https://urn.fi/URN:NBN:fi:aalto-202501302237

Collections

[dipl] Perustieteiden korkeakoulu / SCI