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

In this paper, we present an information-theoretic perspective to groupfairness trade-offs in federated learning (FL) with respect to sensitiveattributes, such as gender, race, etc. Existing works mostly focus on either\emph{global fairness} (overall disparity of the model across all clients) or\emph{local fairness} (disparity of the model at each individual client),without always considering their trade-offs. There is a lack of understandingof the interplay between global and local fairness in FL, and if and when oneimplies the other. To address this gap, we leverage a body of work ininformation theory called partial information decomposition (PID) which firstidentifies three sources of unfairness in FL, namely, \emph{Unique Disparity},\emph{Redundant Disparity}, and \emph{Masked Disparity}. Using canonicalexamples, we demonstrate how these three disparities contribute to global andlocal fairness. This decomposition helps us derive fundamental limits andtrade-offs between global or local fairness, particularly under dataheterogeneity, as well as, derive conditions under which one implies the other.We also present experimental results on benchmark datasets to support ourtheoretical findings. This work offers a more nuanced understanding of thesources of disparity in FL that can inform the use of local disparitymitigation techniques, and their convergence and effectiveness when deployed inpractice.

Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition