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

We propose a model-agnostic approach for mitigating the prediction bias of ablack-box decision-maker, and in particular, a human decision-maker. Our methoddetects in the feature space where the black-box decision-maker is biased andreplaces it with a few short decision rules, acting as a "fair surrogate". Therule-based surrogate model is trained under two objectives, predictiveperformance and fairness. Our model focuses on a setting that is common inpractice but distinct from other literature on fairness. We only have black-boxaccess to the model, and only a limited set of true labels can be queried undera budget constraint. We formulate a multi-objective optimization for building asurrogate model, where we simultaneously optimize for both predictiveperformance and bias. To train the model, we propose a novel training algorithmthat combines a nondominated sorting genetic algorithm with active learning. Wetest our model on public datasets where we simulate various biased "black-box"classifiers (decision-makers) and apply our approach for interpretableaugmented fairness.

Augmented Fairness: An Interpretable Model Augmenting Decision-Makers' Fairness