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 involves a central processor that works with multipleagents to find a global model. The process consists of repeatedly exchangingestimates, which results in the diffusion of information pertaining to thelocal private data. Such a scheme can be inconvenient when dealing withsensitive data, and therefore, there is a need for the privatization of thealgorithms. Furthermore, the current architecture of a server connected tomultiple clients is highly sensitive to communication failures andcomputational overloads at the server. Thus in this work, we develop a privatemulti-server federated learning scheme, which we call graph federated learning.We use cryptographic and differential privacy concepts to privatize thefederated learning algorithm that we extend to the graph structure. We studythe effect of privatization on the performance of the learning algorithm forgeneral private schemes that can be modeled as additive noise. We show underconvexity and Lipschitz conditions, that the privatized process matches theperformance of the non-private algorithm, even when we increase the noisevariance.

A Graph Federated Architecture with Privacy Preserving Learning