… existing federated learning algorithms and experimentally show its improvement in trained
model accuracy, convergence speed, and/or model stability across various machine learning …

… , namely Fast FL (FFL), that jointly and dynamically adjusts the two variables to minimize the
learning error. We demonstrate that FFL consistently achieves higher accuracies faster than …

… of federated learning through assigning distinct weight for participating … federated learning.
In addition, we analyze the convergence bound of gradientdescent based federated learning …

… Federated Learning (FL) coordinates with … federated learning algorithms under arbitrary
device unavailability and propose an algorithm named Memory-augmented Impatient Federated …

… Aiming at improving the efficiency of federated learning with unreliable end devices, we
propose a semi-asynchronous protocol which incorporates a novel client selection algorithm …

Recent attacks on federated learning demonstrate that keeping the training data on clients' …
in an iteration -- a typical scenario in federated learning. In this paper, we propose a secure …

… In this paper, we give an affirmative answer to the above question by proposing a faster …
adaptive gradient method into federated learning. We propose a faster stochastic adaptive FL …

Federated learning (FL) enables clients to collaboratively learn a shared task while keeping
data privacy, which can be adopted at the edge of wireless networks to improve edge …

… called federated learning (FL) has emerged. In each iteration of FL (called round), the edge
devices update local models based on their own data and contribute to the global training by …

… Federated learning (FL) is a distributed learning paradigm that enables a large number of
devices to collaboratively learn … with fast convergence for wireless federated learning,” in IEEE …