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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Federated learning (FL) aims to protect data privacy by enabling clients tobuild machine learning models collaboratively without sharing their privatedata. Recent works demonstrate that information exchanged during FL is subjectto gradient-based privacy attacks and, consequently, a variety ofprivacy-preserving methods have been adopted to thwart such attacks. However,these defensive methods either introduce orders of magnitudes morecomputational and communication overheads (e.g., with homomorphic encryption)or incur substantial model performance losses in terms of prediction accuracy(e.g., with differential privacy). In this work, we propose $\textsc{FedCG}$, anovel federated learning method that leverages conditional generativeadversarial networks to achieve high-level privacy protection while stillmaintaining competitive model performance. $\textsc{FedCG}$ decomposes eachclient's local network into a private extractor and a public classifier andkeeps the extractor local to protect privacy. Instead of exposing extractors,$\textsc{FedCG}$ shares clients' generators with the server for aggregatingclients' shared knowledge aiming to enhance the performance of each client'slocal networks. Extensive experiments demonstrate that $\textsc{FedCG}$ canachieve competitive model performance compared with FL baselines, and privacyanalysis shows that $\textsc{FedCG}$ has a high-level privacy-preservingcapability.

FedCG: Leverage Conditional GAN for Protecting Privacy and Maintaining Competitive Performance in Federated Learning