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

In this paper, we propose the discrete Gaussian based differentially privatefederated learning (D2P-Fed), a unified scheme to achieve both differentialprivacy (DP) and communication efficiency in federated learning (FL). Inparticular, compared with the only prior work taking care of both aspects,D2P-Fed provides stronger privacy guarantee, better composability and smallercommunication cost. The key idea is to apply the discrete Gaussian noise to theprivate data transmission. We provide complete analysis of the privacyguarantee, communication cost and convergence rate of D2P-Fed. We evaluatedD2P-Fed on INFIMNIST and CIFAR10. The results show that D2P-Fed outperformsthe-state-of-the-art by 4.7% to 13.0% in terms of model accuracy while savingone third of the communication cost.

D2P-Fed: Differentially Private Federated Learning With Efficient Communication