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 paradigm for training deep neuralnetworks (DNNs) in distributed manners. Current FL approaches all suffer fromhigh communication overhead and information leakage. In this work, we present afederated learning algorithm based on evolution strategies (FedES), azeroth-order training method. Instead of transmitting model parameters, FedESonly communicates loss values, and thus has very low communication overhead.Moreover, a third party is unable to estimate gradients without knowing thepre-shared seed, which protects data privacy. Experimental results demonstrateFedES can achieve the above benefits while keeping convergence performance thesame as that with back propagation methods.

Communication Efficient and Privacy-Preserving Federated Learning Based on Evolution Strategies