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

Over-the-air federated learning (OTA-FL) exploits the inherent superpositionproperty of wireless channels to integrate the communication and modelaggregation. Though a naturally promising framework for wireless federatedlearning, it requires care to mitigate physical layer impairments. In thiswork, we consider a heterogeneous edge-intelligent network with different edgedevice resources and non-i.i.d. user dataset distributions, under a generalnon-convex learning objective. We leverage the Reconfigurable IntelligentSurface (RIS) technology to augment OTA-FL system over simultaneous timevarying uplink and downlink noisy communication channels under imperfect CSIscenario. We propose a cross-layer algorithm that jointly optimizes RISconfiguration, communication and computation resources in this generalrealistic setting. Specifically, we design dynamic local update steps inconjunction with RIS phase shifts and transmission power to boost learningperformance. We present a convergence analysis of the proposed algorithm, andshow that it outperforms the existing unified approach under heterogeneoussystem and imperfect CSI in numerical results.

RIS-Assisted Over-the-Air Adaptive Federated Learning with Noisy Downlink