FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3092091768> ?p ?o ?g. }

• W3092091768 abstract "Understanding and removing bias from the decisions made by machine learning models is essential to avoid discrimination against unprivileged groups. Despite recent progress in algorithmic fairness, there is still no clear answer as to which bias-mitigation approaches are most effective. Evaluation strategies are typically use-case specific, rely on data with unclear bias, and employ a fixed policy to convert model outputs to decision outcomes. To address these problems, we performed a systematic comparison of a number of popular fairness algorithms applicable to supervised classification. Our study is the most comprehensive of its kind. It utilizes three real and four synthetic datasets, and two different ways of converting model outputs to decisions. It considers fairness, predictive-performance, calibration quality, and speed of 28 different modelling pipelines, corresponding to both fairness-unaware and fairness-aware algorithms. We found that fairness-unaware algorithms typically fail to produce adequately fair models and that the simplest algorithms are not necessarily the fairest ones. We also found that fairness-aware algorithms can induce fairness without material drops in predictive power. Finally, we found that dataset idiosyncracies (e.g., degree of intrinsic unfairness, nature of correlations) do affect the performance of fairness-aware approaches. Our results allow the practitioner to narrow down the approach(es) they would like to adopt without having to know in advance their fairness requirements." @default.
• W3092091768 created "2020-10-15" @default.
• W3092091768 creator A5033090004 @default.
• W3092091768 creator A5035886826 @default.
• W3092091768 creator A5036722312 @default.
• W3092091768 creator A5045686433 @default.
• W3092091768 creator A5077038645 @default.
• W3092091768 creator A5090060572 @default.
• W3092091768 date "2020-10-08" @default.
• W3092091768 modified "2023-10-14" @default.
• W3092091768 title "Metrics and methods for a systematic comparison of fairness-aware machine learning algorithms." @default.
• W3092091768 cites W1979769549 @default.
• W3092091768 cites W2001277584 @default.
• W3092091768 cites W2014352947 @default.
• W3092091768 cites W2087347434 @default.
• W3092091768 cites W2097246321 @default.
• W3092091768 cites W2100960835 @default.
• W3092091768 cites W2101234009 @default.
• W3092091768 cites W2116984840 @default.
• W3092091768 cites W2146807455 @default.
• W3092091768 cites W2162670686 @default.
• W3092091768 cites W2530395818 @default.
• W3092091768 cites W2540757487 @default.
• W3092091768 cites W2550530154 @default.
• W3092091768 cites W2730550703 @default.
• W3092091768 cites W2732560823 @default.
• W3092091768 cites W2753845591 @default.
• W3092091768 cites W2768348081 @default.
• W3092091768 cites W2788284633 @default.
• W3092091768 cites W2788578887 @default.
• W3092091768 cites W2808105152 @default.
• W3092091768 cites W2809878087 @default.
• W3092091768 cites W2888582068 @default.
• W3092091768 cites W2895471314 @default.
• W3092091768 cites W2911964244 @default.
• W3092091768 cites W2946221515 @default.
• W3092091768 cites W2962751370 @default.
• W3092091768 cites W2962977061 @default.
• W3092091768 cites W2963116854 @default.
• W3092091768 cites W2963174898 @default.
• W3092091768 cites W2963178340 @default.
• W3092091768 cites W2963327716 @default.
• W3092091768 cites W2963453196 @default.
• W3092091768 cites W2963917042 @default.
• W3092091768 cites W2964023221 @default.
• W3092091768 cites W2964031043 @default.
• W3092091768 cites W2964060106 @default.
• W3092091768 cites W2964116855 @default.
• W3092091768 cites W2964273229 @default.
• W3092091768 cites W2966613548 @default.
• W3092091768 cites W2997732765 @default.
• W3092091768 cites W3008972592 @default.
• W3092091768 cites W3012438081 @default.
• W3092091768 cites W3017536939 @default.
• W3092091768 cites W3023309920 @default.
• W3092091768 cites W3030081171 @default.
• W3092091768 cites W3092143968 @default.
• W3092091768 cites W3102476541 @default.
• W3092091768 cites W3123374861 @default.
• W3092091768 cites W3125146345 @default.
• W3092091768 cites W3181414820 @default.
• W3092091768 cites W3121556506 @default.
• W3092091768 hasPublicationYear "2020" @default.
• W3092091768 type Work @default.
• W3092091768 sameAs 3092091768 @default.
• W3092091768 citedByCount "0" @default.
• W3092091768 crossrefType "posted-content" @default.
• W3092091768 hasAuthorship W3092091768A5033090004 @default.
• W3092091768 hasAuthorship W3092091768A5035886826 @default.
• W3092091768 hasAuthorship W3092091768A5036722312 @default.
• W3092091768 hasAuthorship W3092091768A5045686433 @default.
• W3092091768 hasAuthorship W3092091768A5077038645 @default.
• W3092091768 hasAuthorship W3092091768A5090060572 @default.
• W3092091768 hasConcept C111472728 @default.
• W3092091768 hasConcept C11413529 @default.
• W3092091768 hasConcept C11867375 @default.
• W3092091768 hasConcept C119857082 @default.
• W3092091768 hasConcept C138885662 @default.
• W3092091768 hasConcept C154945302 @default.
• W3092091768 hasConcept C157764524 @default.
• W3092091768 hasConcept C177972170 @default.
• W3092091768 hasConcept C2778136018 @default.
• W3092091768 hasConcept C2779530757 @default.
• W3092091768 hasConcept C29202148 @default.
• W3092091768 hasConcept C31258907 @default.
• W3092091768 hasConcept C41008148 @default.
• W3092091768 hasConcept C555944384 @default.
• W3092091768 hasConcept C76155785 @default.
• W3092091768 hasConceptScore W3092091768C111472728 @default.
• W3092091768 hasConceptScore W3092091768C11413529 @default.
• W3092091768 hasConceptScore W3092091768C11867375 @default.
• W3092091768 hasConceptScore W3092091768C119857082 @default.
• W3092091768 hasConceptScore W3092091768C138885662 @default.
• W3092091768 hasConceptScore W3092091768C154945302 @default.
• W3092091768 hasConceptScore W3092091768C157764524 @default.
• W3092091768 hasConceptScore W3092091768C177972170 @default.
• W3092091768 hasConceptScore W3092091768C2778136018 @default.
• W3092091768 hasConceptScore W3092091768C2779530757 @default.
• W3092091768 hasConceptScore W3092091768C29202148 @default.
• W3092091768 hasConceptScore W3092091768C31258907 @default.

• next