The use of unmanned aerial vehicles (UAVs) as flying users is becoming a major part of the sixth generation (6G) networks, which could provide various applications, like object detection and video surveillance, by exploiting machine learning (ML) algorithms. However, the training of conventional centralized ML algorithms causes high communication overhead due to the transmission of large datasets and may reveal user privacy. Hence, distributed learning algorithms, including federated learning (FL) and split learning (SL), are proposed to train ML models in a distributed manner via sharing model parameters rather than raw data. Due to the different learning structures, they have different communication and learning efficiency. We propose a new distributed learning architecture, namely hybrid split and federated learning (HSFL), by adopting the parallel model training mechanism of FL and the network splitting structure of SL. Through the simulations in wireless UAV networks, the HSFL algorithm is demonstrated to have higher learning accuracy than FL and less communication overhead than SL under non-IID data. We further propose a Multi-Arm Bandit (MAB) based best channel (BC) and best 2-norm (BN2) (MAB-BC-BN2) UE selection scheme to select the UEs with better channel quality and larger local model updates in each round. Numerical results demonstrate it achieves higher learning accuracy than the benchmarks, BC, MAB-BC, and MAB-BN2 UE selection schemes.
|Title of host publication||IEEE ICC|
|Publisher||IEEE Communications Society|
|Publication status||Accepted/In press - 2022|