New technological advancements in wireless networks have enlarged the number of connected devices. The unprecedented surge of data volume in wireless systems empowered by artificial intelligence (AI) opens up new horizons for providing ubiquitous data-driven intelligent services. Traditional cloudcentric machine learning (ML)-based services are implemented by centrally collecting datasets and training models. However, this conventional training technique encompasses two challenges: (i) high communication and energy cost and (ii) threatened data privacy. In this article, we introduce a comprehensive survey of the fundamentals and enabling technologies of federated learning (FL), a newly emerging technique coined to bring ML to the edge of wireless networks. Moreover, an extensive study is presented detailing various applications of FL in wireless networks and highlighting their challenges and limitations. The efficacy of FL is further explored with emerging prospective beyond fifth-generation (B5G) and sixth-generation (6G) communication systems. This survey aims to provide an overview of the state-ofthe-art FL applications in key wireless technologies that will serve as a foundation to establish a firm understanding of the topic. Lastly, we offer a road forward for future research directions.

翻译：无线网络的新技术进展扩展了联网设备的数量。由人工智能赋能的数据量在无线系统中的空前激增，为提供无处不在的数据驱动智能服务开辟了新前景。传统的以云为中心的基于机器学习的服务通过集中收集数据集和训练模型来实现。然而，这种传统训练技术面临两个挑战：（i）高通信和能源成本，（ii）数据隐私受到威胁。本文全面综述了联邦学习（联邦学习）的基础知识和使能技术——这一新兴技术旨在将机器学习推向无线网络边缘。此外，详细介绍了联邦学习在无线网络中的多种应用，并强调了其挑战与局限性。进一步探讨了联邦学习在面向后5G（B5G）和第六代（6G）通信系统的新兴前景中的有效性。本综述旨在概述联邦学习在关键无线技术中的最新应用，为建立对该主题的深入理解奠定基础。最后，我们为未来的研究方向提供了路线图。