Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classification

Evgenii Chzhen (1, 2, 3) , Christophe Denis (1) , Mohamed Hebiri (1) , Luca Oneto (4) , Massimiliano Pontil (5, 6)

1 LAMA - Laboratoire d'Analyse et de Mathématiques Appliquées
2 LMO - Laboratoire de Mathématiques d'Orsay
3 CELESTE - Statistique mathématique et apprentissage
4 University of Pisa - Università di Pisa
5 IIT - Istituto Italiano di Tecnologia
6 UCL - University College of London [London]

Mots clés: Fairness equality of opportunities; Plug-in classifiers; Semi-supervised classification

Domaines: Statistiques [math.ST]; Machine Learning [stat.ML]; Théorie [stat.TH]

Evgenii Chzhen, Christophe Denis, Mohamed Hebiri, Luca Oneto, Massimiliano Pontil. Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classification. NeurIPS 2019 - 33th Annual Conference on Neural Information Processing Systems, Dec 2019, Vancouver, Canada. ⟨hal-02150662v1⟩