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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Clustered Federated Multitask Learning (CFL) was introduced as an efficientscheme to obtain reliable specialized models when data is imbalanced anddistributed in a non-i.i.d. (non-independent and identically distributed)fashion amongst clients. While a similarity measure metric, like the cosinesimilarity, can be used to endow groups of the client with a specialized model,this process can be arduous as the server should involve all clients in each ofthe federated learning rounds. Therefore, it is imperative that a subset ofclients is selected periodically due to the limited bandwidth and latencyconstraints at the network edge. To this end, this paper proposes a new clientselection algorithm that aims to accelerate the convergence rate for obtainingspecialized machine learning models that achieve high test accuracies for allclient groups. Specifically, we introduce a client selection approach thatleverages the devices' heterogeneity to schedule the clients based on theirround latency and exploits the bandwidth reuse for clients that consume moretime to update the model. Then, the server performs model averaging andclusters the clients based on predefined thresholds. When a specific clusterreaches a stationary point, the proposed algorithm uses a greedy schedulingalgorithm for that group by selecting the clients with less latency to updatethe model. Extensive experiments show that the proposed approach lowers thetraining time and accelerates the convergence rate by up to 50% while imbuingeach client with a specialized model that is fit for its local datadistribution.

Client Selection Approach in Support of Clustered Federated Learning over Wireless Edge Networks