In this letter, a Federated Learning (FL) system where a server does not exist is investigated. In the absence of the server, entire learning process including exchange of model updates is conducted in a distributed manner. Hence, communication protocol is also required to be decentralized. When large number of devices communicate distributively, heavy congestion of communication is inevitable, which leads to huge amount of time for decentralized FL. This letter proposes a novel method to enhance communication efficiency when the decentralized FL system exploits random access protocol. By leveraging the learning characteristics of updates provided by decentralized FL, devices decide on transmission based on their size of dataset, achieving rapid model convergence with low communication overhead. In addition to that, adapting transmission probability is also proposed. Through extensive experiments, we validate our proposed scheme which outperforms existing studies in both case of homogeneous and heterogeneous data distribution.

中文翻译：

---

基于随机访问通道的去中心化联邦学习


在这封信中，调查了一个不存在服务器的联邦学习 （FL） 系统。在没有服务器的情况下，包括模型更新交换在内的整个学习过程以分布式方式进行。因此，通信协议也需要去中心化。当大量设备进行分布式通信时，通信的严重拥塞是不可避免的，这导致去中心化联邦学习的时间非常长。这封信提出了一种在去中心化 FL 系统利用随机访问协议时提高通信效率的新方法。通过利用去中心化联邦学习提供的更新的学习特性，设备可以根据其数据集的大小决定传输，从而以较低的通信开销实现快速模型收敛。除此之外，还提出了调整传输概率的方法。通过广泛的实验，我们验证了我们提出的方案，该方案在同质和异构数据分布的情况下都优于现有研究。