Quantum Federated Learning for Wireless Communications
计算机科学
无线
电信
计算机网络
作者
Rakesh Mohan Pujahari,Akshit Tanwar
出处
期刊:EAI/Springer Innovations in Communication and Computing日期:2022-01-01卷期号:: 215-230被引量:5
标识
DOI:10.1007/978-3-030-85559-8_14
摘要
Quantum federated learning (QFL) architecture for wireless communications is important on account of wireless communication point of view. Different from centralized learning, federated learning offloads the learning tasks into local computation units to improve privacy. The presented QFL is expected to reduce complexity by utilizing quantum computation. The presented two-tier QFL consists of QNN operations in the access points and the cloud. Quantum federated learning is discussed, as well as many potential implementations in 5G networks, as well as key technological issues and open problems for future quantum federated learning research in wireless communications.