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

Due to the dynamics of wireless environment and limited bandwidth, wirelessfederated learning (FL) is challenged by frequent transmission errors andincomplete aggregation from devices. In order to overcome these challenges, wepropose a global model reuse strategy (GoMORE) that reuses the outdated globalmodel to replace the local model parameters once a transmission error occurs.We analytically prove that the proposed GoMORE is strictly superior over theexisting strategy, especially at low signal-to-noise ratios (SNRs). Inaddition, based on the derived expression of weight divergence, we furtheroptimize the number of participating devices in the model aggregation tomaximize the FL performance with limited communication resources. Numericalresults verify that the proposed GoMORE successfully approaches the performanceupper bound by an ideal transmission. It also mitigates the negative impact ofnon-independent and non-identically distributed (non-IID) data while achievingover 5 dB reduction in energy consumption.

GoMORE: Global Model Reuse for Resource-Constrained Wireless Federated Learning