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) has recently emerged as an attractive decentralizedsolution for wireless networks to collaboratively train a shared model whilekeeping data localized. As a general approach, existing FL methods tend toassume perfect knowledge of the Channel State Information (CSI) during thetraining phase, which may not be easy to acquire in case of fast fadingchannels. Moreover, literature analyses either consider a fixed number ofclients participating in the training of the federated model, or simply assumethat all clients operate at the maximum achievable rate to transmit model data.In this paper, we fill these gaps by proposing a training process that takeschannel statistics as a bias to minimize the convergence time under imperfectCSI. Numerical experiments demonstrate that it is possible to reduce thetraining time by neglecting model updates from clients that cannot sustain aminimum predefined transmission rate. We also examine the trade-off betweennumber of clients involved in the training process and model accuracy as afunction of different fading regimes.

On the Convergence Time of Federated Learning Over Wireless Networks Under Imperfect CSI