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

Edge computing has revolutionized the world of mobile and wireless networksworld thanks to its flexible, secure, and performing characteristics. Lately,we have witnessed the increasing use of it to make more performing thedeployment of machine learning (ML) techniques such as federated learning (FL).FL was debuted to improve communication efficiency compared to conventionaldistributed machine learning (ML). The original FL assumes a centralaggregation server to aggregate locally optimized parameters and might bringreliability and latency issues. In this paper, we conduct an in-depth study ofstrategies to replace this central server by a flying master that isdynamically selected based on the current participants and/or availableresources at every FL round of optimization. Specifically, we compare differentmetrics to select this flying master and assess consensus algorithms to performthe selection. Our results demonstrate a significant reduction of runtime usingour flying master FL framework compared to the original FL from measurementsresults conducted in our EdgeAI testbed and over real 5G networks using anoperational edge testbed.

On-the-fly Resource-Aware Model Aggregation for Federated Learning in Heterogeneous Edge