Personalised federated learning with differential privacy and gradient selection

• Main Authors: Lee, Jason Zhi Xin, Ng, Kai Chin, Toh, Arnold Xuan Ming
• 其他作者: Lam Kwok Yan
• 格式: Final Year Project
• 語言: English
• 出版: Nanyang Technological University 2021
• 主題: Engineering::Computer science and engineering::Data
• 在線閱讀: https://hdl.handle.net/10356/151517
• 機構: Nanyang Technological University

The fast-emerging field of federated learning holds the promise of allowing clients to contribute to a central machine learning model without the need to send their data to a central server, thus providing privacy for their data. Two issues arise: dealing with statistical heterogeneity in datasets,...