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 (FL) is an emerging decentralized learning frameworkthrough which multiple clients can collaboratively train a learning model.However, a major obstacle that impedes the wide deployment of FL lies inmassive communication traffic. To train high dimensional machine learningmodels (such as CNN models), heavy communication traffic can be incurred byexchanging model updates via the Internet between clients and the parameterserver (PS), implying that the network resource can be easily exhausted.Compressing model updates is an effective way to reduce the traffic amount.However, a flexible unbiased compression algorithm applicable for both uplinkand downlink compression in FL is still absent from existing works. In thiswork, we devise the Model Update Compression by Soft Clustering (MUCSC)algorithm to compress model updates transmitted between clients and the PS. InMUCSC, it is only necessary to transmit cluster centroids and the cluster ID ofeach model update. Moreover, we prove that: 1) The compressed model updates areunbiased estimation of their original values so that the convergence rate bytransmitting compressed model updates is unchanged; 2) MUCSC can guarantee thatthe influence of the compression error on the model accuracy is minimized.Then, we further propose the boosted MUCSC (B-MUCSC) algorithm, a biasedcompression algorithm that can achieve an extremely high compression rate bygrouping insignificant model updates into a super cluster. B-MUCSC is suitablefor scenarios with very scarce network resource. Ultimately, we conductextensive experiments with the CIFAR-10 and FEMNIST datasets to demonstratethat our algorithms can not only substantially reduce the volume ofcommunication traffic in FL, but also improve the training efficiency inpractical networks.

Slashing Communication Traffic in Federated Learning by Transmitting Clustered Model Updates