… As such, distributed machine learning is well motivated to overcome these … learning,
federated learning (FL) has been proposed as a well noted approach for collaborative learning [3]. …

… Abstract—Air access networks have been recognized as a … In particular, the aerial computing
network infrastructure … semi-supervised federated learning framework for aerial computing, …

… may incur huge network traffic and drone data privacy leakage. Federated learning (FL) is
… privacy by performing local training in drones and sharing training model parameters in the …

… In [23], an IRS was deployed to minimize the transmit power of the multi-antenna access
point (AP) by jointly optimizing active and passive beamforming, while satisfying the signal-to-…

… UAVs (Unmanned aerial vehicles) are being utilised more frequently in wireless … Monte
Carlo federated learning based access network. Then the routing through UAV network has been …

… of ML models in general, we focus specifically on DNN model training in this section as a
majority of the papers that we subsequently review study the federated training of DNN models. …

… We study the variation in the average packet delay in federated learning scenario. Here,
we vary the number of vehicles (V) and the vehicle velocity under different road lengths (RL). …

… Channel and Signal Modeling We consider two distinct types of waveforms over aerial
channels. Let x [m] n be the transmitted signal by the n-th legitimate user, Un, to the m-th UAV CH …

… federated edge learning (FEEL) in unmanned aerial vehicle (UAV)-enabled Internet of
Things (IoT) for B5G/6G networks… to complete more training rounds of federated learning is an …

… , federated learning (FL) is becoming a potential solution to perform training tasks locally on
… In 5G and beyond networks, unmanned aerial vehicle (UAV)-assisted MEC is envisioned as …