… federated learning (FL), a popular technique in distributed learning, where a CS coordinates
global model training … Instead of sharing local data, the parameters of the machine learning (…

… and wireless devices, federated learning (FL) over wireless … of electromagnetic waves,
over-the-air computation (AirComp) … However, sharing frequency-time resources in over-the-air …

… (NOMA) and over-the-air federated learning (AirFL) into a unified … This analysis reveals that
the learning performance is … Furthermore, when the learning rate diminishes as the training …

… to train a global model from the diverse distributed data over the edge devices [2]. However,
… approach is federated learning (FL), which is able to implement machine learning directly at …

… Federated learning (FL) is a promising solution to enable many AI applications, where … for
collaboratively training a global model. FL allows the clients to participate in the training phase, …

… their raw data locally, over-the-air federated learning (AirFL) is greatly desired in many
resourcelimited and privacy-sensitive scenarios empowered by largescale machine learning [6], […

… problem in over-the-air computation (AirComp) for federated learning. Since the learning
performance improves as more devices participate in the federated learning aggregation, we …

… Abstract—We consider federated edge learning among … In particular, we consider energy
harvesting FL with over-the-air … local updates simultaneously over the same channel bandwidth…

… ABSTRACT This paper investigates the deployment of federated learning (FL) over an
over-the-air computation (AirComp) and intelligent reflecting surface (IRS) based wireless network…

… Federated Learning We consider an FL system consisting of a server and 𝑁 devices, all of
which are equipped with a single antenna. Let N ≜ {1,...,𝑁} denote the set of devices. Each …