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

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...

Full description

Bibliographic Details
Main Authors: Qiu, Hongyu, Wang, Yongwei, Xu, Yonghui, Cui, Lizhen, Shen, Zhiqi
Other Authors: School of Computer Science and Engineering
Format: Conference Paper
Language:English
Published: 2024
Subjects:
Online Access:https://hdl.handle.net/10356/173926