FedCIO: efficient exact federated unlearning with clustering, isolation, and one-shot aggregation

• Main Authors: Qiu, Hongyu, Wang, Yongwei, Xu, Yonghui, Cui, Lizhen, Shen, Zhiqi
• 其他作者: School of Computer Science and Engineering
• 格式: Conference or Workshop Item
• 語言: English
• 出版: 2024
• 主題: Computer and Information Science; Federated learning; Machine unlearning
• 在線閱讀: https://hdl.handle.net/10356/173926
• 機構: Nanyang Technological University

Data are invaluable in machine learning (ML), yet they raise significant privacy concerns. In the real world, data are often distributed across isolated silos, challenging conventional ML methods that centralize data. Federated learning (FL) offers a privacy-preserving solution that enables learning...