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

As in traditional machine learning models, models trained with federatedlearning may exhibit disparate performance across demographic groups. Modelholders must identify these disparities to mitigate undue harm to the groups.However, measuring a model's performance in a group requires access toinformation about group membership which, for privacy reasons, often haslimited availability. We propose novel locally differentially privatemechanisms to measure differences in performance across groups while protectingthe privacy of group membership. To analyze the effectiveness of themechanisms, we bound their error in estimating a disparity when optimized for agiven privacy budget. Our results show that the error rapidly decreases forrealistic numbers of participating clients, demonstrating that, contrary towhat prior work suggested, protecting privacy is not necessarily in conflictwith identifying performance disparities of federated models.

"You Can't Fix What You Can't Measure": Privately Measuring Demographic Performance Disparities in Federated Learning