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 is a new learning scheme for collaborative training ashared prediction model while keeping data locally on participating devices. Inthis paper, we study a new model of multiple federated learning services at themulti-access edge computing server. Accordingly, the sharing of CPU resourcesamong learning services at each mobile device for the local training processand allocating communication resources among mobile devices for exchanginglearning information must be considered. Furthermore, the convergenceperformance of different learning services depends on the hyper-learning rateparameter that needs to be precisely decided. Towards this end, we propose ajoint resource optimization and hyper-learning rate control problem, namelyMS-FEDL, regarding the energy consumption of mobile devices and overalllearning time. We design a centralized algorithm based on the block coordinatedescent method and a decentralized JP-miADMM algorithm for solving the MS-FEDLproblem. Different from the centralized approach, the decentralized approachrequires many iterations to obtain but it allows each learning service toindependently manage the local resource and learning process without revealingthe learning service information. Our simulation results demonstrate theconvergence performance of our proposed algorithms and the superior performanceof our proposed algorithms compared to the heuristic strategy.

Toward Multiple Federated Learning Services Resource Sharing in Mobile Edge Networks