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

Federated learning (FL) enables participating parties to collaborativelybuild a global model with boosted utility without disclosing private datainformation. Appropriate protection mechanisms have to be adopted to fulfillthe requirements in preserving \textit{privacy} and maintaining high model\textit{utility}. The nature of the widely-adopted protection mechanismsincluding \textit{Randomization Mechanism} and \textit{Compression Mechanism}is to protect privacy via distorting model parameter. We measure the utilityvia the gap between the original model parameter and the distorted modelparameter. We want to identify under what general conditions privacy-preservingfederated learning can achieve near-optimal utility via data generation andparameter distortion. To provide an avenue for achieving near-optimal utility,we present an upper bound for utility loss, which is measured using two mainterms called variance-reduction and model parameter discrepancy separately. Ouranalysis inspires the design of appropriate protection parameters for theprotection mechanisms to achieve near-optimal utility and meet the privacyrequirements simultaneously. The main techniques for the protection mechanisminclude parameter distortion and data generation, which are generic and can beapplied extensively. Furthermore, we provide an upper bound for the trade-offbetween privacy and utility, which together with the lower bound illustrated inNFL form the conditions for achieving optimal trade-off.

Towards Achieving Near-optimal Utility for Privacy-Preserving Federated Learning via Data Generation and Parameter Distortion