Adaptive Federated Learning Architecture To Mitigate Non-IID Through Multi-Objective GA-Based Efficient Client Selection

Federated Learning (FL) has emerged as a promising framework for collaborative model training across distributed devices without centralizing sensitive data. However, FL encounters significant challenges when dealing with non-independent and non-identically distributed (Non-IID) data across particip...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Ajaj, Mohamad (author)
التنسيق: masterThesis
منشور في: 2024
الوصول للمادة أونلاين:http://hdl.handle.net/10725/16528
https://doi.org/10.26756/th.2023.748
http://libraries.lau.edu.lb/research/laur/terms-of-use/thesis.php
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513472901939200
author Ajaj, Mohamad
author_facet Ajaj, Mohamad
author_role author
dc.creator.none.fl_str_mv Ajaj, Mohamad
dc.date.none.fl_str_mv 2024
2024-11-12
2025-02-07T14:12:49Z
2025-02-07T14:12:49Z
dc.identifier.none.fl_str_mv http://hdl.handle.net/10725/16528
https://doi.org/10.26756/th.2023.748
http://libraries.lau.edu.lb/research/laur/terms-of-use/thesis.php
dc.language.none.fl_str_mv en
dc.publisher.none.fl_str_mv Lebanese American University
dc.rights.*.fl_str_mv info:eu-repo/semantics/openAccess
dc.title.none.fl_str_mv Adaptive Federated Learning Architecture To Mitigate Non-IID Through Multi-Objective GA-Based Efficient Client Selection
dc.type.none.fl_str_mv Thesis
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/masterThesis
description Federated Learning (FL) has emerged as a promising framework for collaborative model training across distributed devices without centralizing sensitive data. However, FL encounters significant challenges when dealing with non-independent and non-identically distributed (Non-IID) data across participating clients, such as skewed label distributions and varying data quantities. Existing solutions still have several constraints leading to suboptimal model performance and slow convergence. In this paper, we propose a novel approach that incorporates genetic algorithms with an enhanced client selection strategy, utilizing client metadata rather than raw data. Our approach not only mitigates the impact of non-IID data by selecting clients with diverse and representative data distributions, but also enables continuous assessment after each training round without compromising model performance. We demonstrate the effectiveness of our approach through extensive experimentation using the MNIST, CIFAR-10, and FeKDD datasets. Our results show a significant reduction in communication overhead and enhancement in overall FL performance compared to random client selection methods. This research provides practical insights and solutions for using FL in real-world scenarios with diverse data distributions.
eu_rights_str_mv openAccess
format masterThesis
id LAURepo_599d0527c630ecbfd9d0a2d5d9fe67d2
language_invalid_str_mv en
network_acronym_str LAURepo
network_name_str Lebanese American University repository
oai_identifier_str oai:laur.lau.edu.lb:10725/16528
publishDate 2024
publisher.none.fl_str_mv Lebanese American University
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Adaptive Federated Learning Architecture To Mitigate Non-IID Through Multi-Objective GA-Based Efficient Client SelectionAjaj, MohamadFederated Learning (FL) has emerged as a promising framework for collaborative model training across distributed devices without centralizing sensitive data. However, FL encounters significant challenges when dealing with non-independent and non-identically distributed (Non-IID) data across participating clients, such as skewed label distributions and varying data quantities. Existing solutions still have several constraints leading to suboptimal model performance and slow convergence. In this paper, we propose a novel approach that incorporates genetic algorithms with an enhanced client selection strategy, utilizing client metadata rather than raw data. Our approach not only mitigates the impact of non-IID data by selecting clients with diverse and representative data distributions, but also enables continuous assessment after each training round without compromising model performance. We demonstrate the effectiveness of our approach through extensive experimentation using the MNIST, CIFAR-10, and FeKDD datasets. Our results show a significant reduction in communication overhead and enhancement in overall FL performance compared to random client selection methods. This research provides practical insights and solutions for using FL in real-world scenarios with diverse data distributions.Lebanese American University2025-02-07T14:12:49Z2025-02-07T14:12:49Z20242024-11-12Thesisinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesishttp://hdl.handle.net/10725/16528https://doi.org/10.26756/th.2023.748http://libraries.lau.edu.lb/research/laur/terms-of-use/thesis.phpeninfo:eu-repo/semantics/openAccessoai:laur.lau.edu.lb:10725/165282025-02-07T14:12:49Z
spellingShingle Adaptive Federated Learning Architecture To Mitigate Non-IID Through Multi-Objective GA-Based Efficient Client Selection
Ajaj, Mohamad
status_str publishedVersion
title Adaptive Federated Learning Architecture To Mitigate Non-IID Through Multi-Objective GA-Based Efficient Client Selection
title_full Adaptive Federated Learning Architecture To Mitigate Non-IID Through Multi-Objective GA-Based Efficient Client Selection
title_fullStr Adaptive Federated Learning Architecture To Mitigate Non-IID Through Multi-Objective GA-Based Efficient Client Selection
title_full_unstemmed Adaptive Federated Learning Architecture To Mitigate Non-IID Through Multi-Objective GA-Based Efficient Client Selection
title_short Adaptive Federated Learning Architecture To Mitigate Non-IID Through Multi-Objective GA-Based Efficient Client Selection
title_sort Adaptive Federated Learning Architecture To Mitigate Non-IID Through Multi-Objective GA-Based Efficient Client Selection
url http://hdl.handle.net/10725/16528
https://doi.org/10.26756/th.2023.748
http://libraries.lau.edu.lb/research/laur/terms-of-use/thesis.php