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

In this study, we propose an over-the-air computation (AirComp) scheme forfederated edge learning (FEEL). The proposed scheme relies on the concept ofdistributed learning by majority vote (MV) with sign stochastic gradientdescend (signSGD). As compared to the state-of-the-art solutions, with theproposed method, edge devices (EDs) transmit the signs of local stochasticgradients by activating one of two orthogonal resources, i.e., orthogonalfrequency division multiplexing (OFDM) subcarriers, and the MVs at the edgeserver (ES) are obtained with non-coherent detectors by exploiting the energyaccumulations on the subcarriers. Hence, the proposed scheme eliminates theneed for channel state information (CSI) at the EDs and ES. By taking pathloss, power control, cell size, and the probabilistic nature of the detectedMVs in fading channel into account, we prove the convergence of the distributedlearning for a non-convex function. Through simulations, we show that theproposed scheme can provide a high test accuracy in fading channels even whenthe time-synchronization and the power alignment at the ES are not ideal. Wealso provide insight into distributed learning for location-dependent datadistribution for the MV-based schemes.

Distributed Learning over a Wireless Network with FSK-Based Majority Vote