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

The goal of fairness in classification is to learn a classifier that does notdiscriminate against groups of individuals based on sensitive attributes, suchas race and gender. One approach to designing fair algorithms is to userelaxations of fairness notions as regularization terms or in a constrainedoptimization problem. We observe that the hyperbolic tangent function canapproximate the indicator function. We leverage this property to define adifferentiable relaxation that approximates fairness notions provably betterthan existing relaxations. In addition, we propose a model-agnosticmulti-objective architecture that can simultaneously optimize for multiplefairness notions and multiple sensitive attributes and supports all statisticalparity-based notions of fairness. We use our relaxation with themulti-objective architecture to learn fair classifiers. Experiments on publicdatasets show that our method suffers a significantly lower loss of accuracythan current debiasing algorithms relative to the unconstrained model.

Addressing Fairness in Classification with a Model-Agnostic Multi-Objective Algorithm