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

Fairness testing aims at mitigating unintended discrimination in thedecision-making process of data-driven AI systems. Individual discriminationmay occur when an AI model makes different decisions for two distinctindividuals who are distinguishable solely according to protected attributes,such as age and race. Such instances reveal biased AI behaviour, and are calledIndividual Discriminatory Instances (IDIs).  In this paper, we propose an approach for the selection of the initial seedsto generate IDIs for fairness testing. Previous studies mainly used randominitial seeds to this end. However this phase is crucial, as these seeds arethe basis of the follow-up IDIs generation. We dubbed our proposed seedselection approach I&D. It generates a large number of initial IDIs exhibitinga great diversity, aiming at improving the overall performance of fairnesstesting.  Our empirical study reveal that I&D is able to produce a larger number ofIDIs with respect to four state-of-the-art seed generation approaches,generating 1.68X more IDIs on average. Moreover, we compare the use of I&D totrain machine learning models and find that using I&D reduces the number ofremaining IDIs by 29% when compared to the state-of-the-art, thus indicatingthat I&D is effective for improving model fairness

Enhanced Fairness Testing via Generating Effective Initial Individual Discriminatory Instances