… the joint device selection and power control scheme for wireless federated learning (FL), con…
the parameter server (PS) and the terminal devices. In each round of model training, the PS …

… Federated Learning (FL) setup, a number of devices contribute to the training of a common
model. We present a method for selecting the devices … , and better device-level performance. …

… lack of any participating devices. In this study, we consider device selection based on downlink
channels over which the PS shares the global model with the devices. Performing digital …

… Abstract—As a privacy-preserving paradigm for training Machine Learning (ML) models,
Federated Learning (FL) has received tremendous attention from both industry and academia. …

… For the device selection problem, we train the K-means to perform device clustering while
… Then, we carry out device selection based on the weight divergence between the local …

… for federated learning with partial device participation with any biased client selection
strategy. We discover that biasing client selection can speed up the convergence at the rate O( 1 …

… seek to design a federated learning approach which respects the privacy of each device’s
data and at … We use Oort as a baseline for being the state-of-the-art device selection policy that …

… for each device is different. To solve the above problems for federated learning in wireless
… longterm FL process with energy-limited edge devices, to reduce the time-averaged cost of …

… machine learning applications. Federated Learning is thus developed to offer decentralized
learning on user devices. However, it is difficult to jointly address multiple issues such as …

… Instead of random selection, we show that selecting devices with a clustering algorithm can
… DRL FOR CLIENT SELECTION We formulate device selection for federated learning as a …