Personalized federated learning with dynamic clustering and model distillation

• Main Author: Bao, Junyan
• Other Authors: Tay Wee Peng
• Format: Thesis-Master by Coursework
• Language: English
• Published: Nanyang Technological University 2025
• Subjects: Computer and Information Science; Federated learning; Hierarchical clustering; Knowledge distillation
• Online Access: https://hdl.handle.net/10356/181935
• Institution: Nanyang Technological University

Federated learning is a distributed machine learning technique that allows various data sources to work together to train models while keeping their raw data private. However, federated learning faces many challenges when dealing with non-independent and identically distributed (Non-IID) data, espec...