Matches in SemOpenAlex for { <https://semopenalex.org/work/W2911457688> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2911457688 abstract "Motivated by concerns that machine learning algorithms may introduce significant bias in classification models, developing fair classifiers has become an important problem in machine learning research. One important paradigm towards this has been providing algorithms for adversarially learning fair classifiers (Zhang et al., 2018; Madras et al., 2018). We formulate the adversarial learning problem as a multi-objective optimization problem and find the fair model using gradient descent-ascent algorithm with a modified gradient update step, inspired by the approach of Zhang et al., 2018. We provide theoretical insight and guarantees that formalize the heuristic arguments presented previously towards taking such an approach. We test our approach empirically on the Adult dataset and synthetic datasets and compare against state of the art algorithms (Celis et al., 2018; Zhang et al., 2018; Zafar et al., 2017). The results show that our models and algorithms have comparable or better accuracy than other algorithms while performing better in terms of fairness, as measured using statistical rate or false discovery rate." @default.
- W2911457688 created "2019-02-21" @default.
- W2911457688 creator A5054251740 @default.
- W2911457688 creator A5080439623 @default.
- W2911457688 date "2019-01-29" @default.
- W2911457688 modified "2023-09-27" @default.
- W2911457688 title "Improved Adversarial Learning for Fair Classification." @default.
- W2911457688 cites W1453222892 @default.
- W2911457688 cites W1648303880 @default.
- W2911457688 cites W2014352947 @default.
- W2911457688 cites W2039612585 @default.
- W2911457688 cites W2069317438 @default.
- W2911457688 cites W2097477220 @default.
- W2911457688 cites W2099471712 @default.
- W2911457688 cites W2100960835 @default.
- W2911457688 cites W2116984840 @default.
- W2911457688 cites W2121210949 @default.
- W2911457688 cites W2124768887 @default.
- W2911457688 cites W2149252982 @default.
- W2911457688 cites W2162670686 @default.
- W2911457688 cites W2530395818 @default.
- W2911457688 cites W2540757487 @default.
- W2911457688 cites W2584805976 @default.
- W2911457688 cites W2594166818 @default.
- W2911457688 cites W2767437859 @default.
- W2911457688 cites W2778670458 @default.
- W2911457688 cites W2788241675 @default.
- W2911457688 cites W2788416960 @default.
- W2911457688 cites W2790025105 @default.
- W2911457688 cites W2790744245 @default.
- W2911457688 cites W2805173664 @default.
- W2911457688 cites W2810290439 @default.
- W2911457688 cites W2963100392 @default.
- W2911457688 cites W2963116854 @default.
- W2911457688 cites W2963174898 @default.
- W2911457688 cites W2963178340 @default.
- W2911457688 cites W2963779314 @default.
- W2911457688 cites W2963830794 @default.
- W2911457688 cites W3023309920 @default.
- W2911457688 hasPublicationYear "2019" @default.
- W2911457688 type Work @default.
- W2911457688 sameAs 2911457688 @default.
- W2911457688 citedByCount "14" @default.
- W2911457688 countsByYear W29114576882019 @default.
- W2911457688 countsByYear W29114576882020 @default.
- W2911457688 countsByYear W29114576882021 @default.
- W2911457688 crossrefType "posted-content" @default.
- W2911457688 hasAuthorship W2911457688A5054251740 @default.
- W2911457688 hasAuthorship W2911457688A5080439623 @default.
- W2911457688 hasConcept C11413529 @default.
- W2911457688 hasConcept C119857082 @default.
- W2911457688 hasConcept C153258448 @default.
- W2911457688 hasConcept C154945302 @default.
- W2911457688 hasConcept C173801870 @default.
- W2911457688 hasConcept C17744445 @default.
- W2911457688 hasConcept C191935318 @default.
- W2911457688 hasConcept C199539241 @default.
- W2911457688 hasConcept C2777045944 @default.
- W2911457688 hasConcept C37736160 @default.
- W2911457688 hasConcept C41008148 @default.
- W2911457688 hasConcept C50644808 @default.
- W2911457688 hasConceptScore W2911457688C11413529 @default.
- W2911457688 hasConceptScore W2911457688C119857082 @default.
- W2911457688 hasConceptScore W2911457688C153258448 @default.
- W2911457688 hasConceptScore W2911457688C154945302 @default.
- W2911457688 hasConceptScore W2911457688C173801870 @default.
- W2911457688 hasConceptScore W2911457688C17744445 @default.
- W2911457688 hasConceptScore W2911457688C191935318 @default.
- W2911457688 hasConceptScore W2911457688C199539241 @default.
- W2911457688 hasConceptScore W2911457688C2777045944 @default.
- W2911457688 hasConceptScore W2911457688C37736160 @default.
- W2911457688 hasConceptScore W2911457688C41008148 @default.
- W2911457688 hasConceptScore W2911457688C50644808 @default.
- W2911457688 hasLocation W29114576881 @default.
- W2911457688 hasOpenAccess W2911457688 @default.
- W2911457688 hasPrimaryLocation W29114576881 @default.
- W2911457688 hasRelatedWork W2014352947 @default.
- W2911457688 hasRelatedWork W2099471712 @default.
- W2911457688 hasRelatedWork W2100960835 @default.
- W2911457688 hasRelatedWork W2116666691 @default.
- W2911457688 hasRelatedWork W2116984840 @default.
- W2911457688 hasRelatedWork W2162670686 @default.
- W2911457688 hasRelatedWork W2530395818 @default.
- W2911457688 hasRelatedWork W2540757487 @default.
- W2911457688 hasRelatedWork W2546563948 @default.
- W2911457688 hasRelatedWork W2809878087 @default.
- W2911457688 hasRelatedWork W2810290439 @default.
- W2911457688 hasRelatedWork W2917340714 @default.
- W2911457688 hasRelatedWork W2962790618 @default.
- W2911457688 hasRelatedWork W2963100392 @default.
- W2911457688 hasRelatedWork W2963116854 @default.
- W2911457688 hasRelatedWork W2963174898 @default.
- W2911457688 hasRelatedWork W2963178340 @default.
- W2911457688 hasRelatedWork W2963327716 @default.
- W2911457688 hasRelatedWork W2964031043 @default.
- W2911457688 hasRelatedWork W3023309920 @default.
- W2911457688 isParatext "false" @default.
- W2911457688 isRetracted "false" @default.
- W2911457688 magId "2911457688" @default.
- W2911457688 workType "article" @default.