Federated Learning (FL) has been considered as an appealing framework to tackle data privacy issues of mobile devices compared to conventional Machine Learning (ML). Using Edge Servers (ESs) as intermediaries to perform model aggregation in proximity can reduce the transmission overhead, and it enables great potentials in low-latency FL, where the hierarchical architecture of FL (HFL) has been attracted more attention. Designing a proper client selection policy can significantly improve training performance, and it has been extensively used in FL studies. However, to the best of our knowledge, there are no studies focusing on HFL. In addition, client selection for HFL faces more challenges than conventional FL, e.g., the time-varying connection of client-ES pairs and the limited budget of the Network Operator (NO). In this paper, we investigate a client selection problem for HFL, where the NO learns the number of successful participating clients to improve the training performance (i.e., select as many clients in each round) as well as under the limited budget on each ES. An online policy, called Context-aware Online Client Selection (COCS), is developed based on Contextual Combinatorial Multi-Armed Bandit (CC-MAB). COCS observes the side-information (context) of local computing and transmission of client-ES pairs and makes client selection decisions to maximize NO's utility given a limited budget. Theoretically, COCS achieves a sublinear regret compared to an Oracle policy on both strongly convex and non-convex HFL. Simulation results also support the efficiency of the proposed COCS policy on real-world datasets.

翻译：联邦学习联合会(FL)被认为是解决移动设备数据隐私问题与常规机器学习(ML)相比,解决移动设备数据隐私问题的诱人框架。使用边缘服务器(ESs)作为在近距离进行模型聚合的中间机构,可以减少传输管理费用,并使得低延迟FL(FL(HFL)的等级结构受到更多关注)具有巨大的潜力。设计适当的客户选择政策可以大大改善培训业绩,并在FL研究中广泛使用。然而,根据我们的知识,没有以HFL(ML)为重点开展研究。 此外,使用边缘服务器(ES)的客户选择比常规FL(ML)面临更多挑战,例如,客户-ES配对的时间变化式连接和网络操作员(NO)的预算有限。 在本文中,我们调查低延迟的FL(HL(HL)的等级结构架构)客户选择问题,让成功的参与客户数量提高培训业绩(即,在每轮中选择多少客户,以及在每个ES(CFL)的有限预算下,称为内部在线客户选择(CO)在线客户选择(OC(OC),在内部客户端的客户端交付数据中,也通过O-CSLO-CS-CS-CS-CFL-CS-CS-CS-CFOL-CS-del-CS-delal-C-del-del-del-del-de-de-del-del-del-de-del-del-del-del-del-de-de-del-del-del-de-del-de-deal-de-de-de-cal-cal-del-deal-deal-de-de-de-del-de-de-de-de-de-de-de-de-de-de-de-de-deal-cal-cal-deal-cal-cal-de-de-deal-cal-cal-cal-cal-deal-deal-deal-deal-de-deal-deal-de-de-cal-cal-de-de-cal-de-de-de-de-de-de-cal-cal-de-cal-de-de-de-de-de-de-