English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Federated learning (FL) is a useful tool in distributed machine learning thatutilizes users' local datasets in a privacy-preserving manner. When deployingFL in a constrained wireless environment; however, training models in atime-efficient manner can be a challenging task due to intermittentconnectivity of devices, heterogeneous connection quality, and non-i.i.d. data.In this paper, we provide a novel convergence analysis of non-convex lossfunctions using FL on both i.i.d. and non-i.i.d. datasets with arbitrary deviceselection probabilities for each round. Then, using the derived convergencebound, we use stochastic optimization to develop a new client selection andpower allocation algorithm that minimizes a function of the convergence boundand the average communication time under a transmit power constraint. We findan analytical solution to the minimization problem. One key feature of thealgorithm is that knowledge of the channel statistics is not required and onlythe instantaneous channel state information needs to be known. Using theFEMNIST and CIFAR-10 datasets, we show through simulations that thecommunication time can be significantly decreased using our algorithm, comparedto uniformly random participation.

Communication-Efficient Device Scheduling for Federated Learning Using Stochastic Optimization