Federated Learning for Collaborative Model Training

Thesis Abstract

Federated learning has emerged as a promising approach for training machine learning models across decentralized devices while preserving data privacy. This project aims to investigate the principles and applications of federated learning in collaborative model training. The project will explore the architecture of federated learning systems, communication protocols, and optimization algorithms for model aggregation. Additionally, the project will analyze the potential applications of federated learning in healthcare, finance, and edge computing environments.