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 seeks to address the issue of isolated data islands bymaking clients disclose only their local training models. However, it wasdemonstrated that private information could still be inferred by analyzinglocal model parameters, such as deep neural network model weights. Recently,differential privacy has been applied to federated learning to protect dataprivacy, but the noise added may degrade the learning performance much.Typically, in previous work, training parameters were clipped equally andnoises were added uniformly. The heterogeneity and convergence of trainingparameters were simply not considered. In this paper, we propose adifferentially private scheme for federated learning with adaptive noise (AdapDP-FL). Specifically, due to the gradient heterogeneity, we conduct adaptivegradient clipping for different clients and different rounds; due to thegradient convergence, we add decreasing noises accordingly. Extensiveexperiments on real-world datasets demonstrate that our Adap DP-FL outperformsprevious methods significantly.

Adap DP-FL: Differentially Private Federated Learning with Adaptive Noise