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

With the rapid growth of edge intelligence, the deployment of federatedlearning (FL) over wireless networks has garnered increasing attention, whichis called Federated Edge Learning (FEEL). In FEEL, both mobile devicestransmitting model parameters over noisy channels and collecting data indiverse environments pose challenges to the generalization of trained models.Moreover, devices can engage in decentralized FL via Device-to-Devicecommunication while the communication topology of connected devices alsoimpacts the generalization of models. Most recent theoretical studies overlookthe incorporation of all these effects into FEEL when developing generalizationanalyses. In contrast, our work presents an information-theoreticgeneralization analysis for topology-aware FEEL in the presence of dataheterogeneity and noisy channels. Additionally, we propose a novelregularization method called Federated Global Mutual Information Reduction(FedGMIR) to enhance the performance of models based on our analysis. Numericalresults validate our theoretical findings and provide evidence for theeffectiveness of the proposed method.

Information-Theoretic Generalization Analysis for Topology-aware Heterogeneous Federated Edge Learning over Noisy Channels