Uncovering the Potential of Federated Learning: Addressing Algorithmic and Data-driven Challenges under Privacy Restrictions

Jafarigol, Elaheh

Uncovering the Potential of Federated Learning: Addressing Algorithmic and Data-driven Challenges under Privacy Restrictions

dc.contributor.advisor	Trafalis, Theodore
dc.contributor.author	Jafarigol, Elaheh
dc.contributor.committeeMember	Razzaghi, Talayeh
dc.contributor.committeeMember	Diochnos, Dimitrios
dc.contributor.committeeMember	Siddique, Zahed
dc.date.accessioned	2023-12-01T15:51:39Z
dc.date.available	2023-12-01T15:51:39Z
dc.date.issued	2023-12-15
dc.date.manuscript	2023-11-15
dc.description.abstract	Federated learning is a groundbreaking distributed machine learning paradigm that allows for the collaborative training of models across various entities without directly sharing sensitive data, ensuring privacy and robustness. This Ph.D. dissertation delves into the intricacies of federated learning, investigating the algorithmic and data-driven challenges of deep learning models in the presence of additive noise in this framework. The main objective is to provide strategies to measure the generalization, stability, and privacy-preserving capabilities of these models and further improve them. To this end, five noise infusion mechanisms at varying noise levels within centralized and federated learning settings are explored. As model complexity is a key component of the generalization and stability of deep learning models during training and evaluation, a comparative analysis of three Convolutional Neural Network (CNN) architectures is provided. A key contribution of this study is introducing specific metrics for training with noise. Signal-to-Noise Ratio (SNR) is introduced as a quantitative measure of the trade-off between privacy and training accuracy of noise-infused models, aiming to find the noise level that yields optimal privacy and accuracy. Moreover, the Price of Stability and Price of Anarchy are defined in the context of privacy-preserving deep learning, contributing to the systematic investigation of the noise infusion mechanisms to enhance privacy without compromising performance. This research sheds light on the delicate balance between these critical factors, fostering a deeper understanding of the implications of noise-based regularization in machine learning. The present study also explores a real-world application of federated learning in weather prediction applications that suffer from the issue of imbalanced datasets. Utilizing data from multiple sources combined with advanced data augmentation techniques improves the accuracy and generalization of weather prediction models, even when dealing with imbalanced datasets. Overall, federated learning is pivotal in harnessing decentralized datasets for real-world applications while safeguarding privacy. By leveraging noise as a tool for regularization and privacy enhancement, this research study aims to contribute to the development of robust, privacy-aware algorithms, ensuring that AI-driven solutions prioritize both utility and privacy.	en_US
dc.identifier.uri	https://hdl.handle.net/11244/339990
dc.language	en_US	en_US
dc.rights	Attribution-NonCommercial-NoDerivatives 4.0 International	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/4.0/	*
dc.subject	Machine learning	en_US
dc.subject	Artificial intelligence	en_US
dc.subject	Privacy	en_US
dc.subject	Federated learning	en_US
dc.thesis.degree	Ph.D.	en_US
dc.title	Uncovering the Potential of Federated Learning: Addressing Algorithmic and Data-driven Challenges under Privacy Restrictions	en_US
ou.group	Gallogly College of Engineering	en_US
shareok.orcid	0000-0002-0294-3454	en_US