Synthetic Data Generation for Intersectional ...
Type de document :
Pré-publication ou Document de travail
Titre :
Synthetic Data Generation for Intersectional Fairness by Leveraging Hierarchical Group Structure
Auteur(s) :
Maheshwari, Gaurav [Auteur]
Machine Learning in Information Networks [MAGNET]
Bellet, Aurelien [Auteur]
Institut Desbrest de santé publique [IDESP]
Médecine de précision par intégration de données et inférence causale [PREMEDICAL]
Denis, Pascal [Auteur]
Machine Learning in Information Networks [MAGNET]
Keller, Mikaela [Auteur]
Machine Learning in Information Networks [MAGNET]
Machine Learning in Information Networks [MAGNET]
Bellet, Aurelien [Auteur]

Institut Desbrest de santé publique [IDESP]
Médecine de précision par intégration de données et inférence causale [PREMEDICAL]
Denis, Pascal [Auteur]

Machine Learning in Information Networks [MAGNET]
Keller, Mikaela [Auteur]

Machine Learning in Information Networks [MAGNET]
Date de publication :
2024-05-23
Discipline(s) HAL :
Informatique [cs]/Apprentissage [cs.LG]
Résumé en anglais : [en]
In this paper, we introduce a data augmentation approach specifically tailored to enhance intersectional fairness in classification tasks. Our method capitalizes on the hierarchical structure inherent to intersectionality, ...
Lire la suite >In this paper, we introduce a data augmentation approach specifically tailored to enhance intersectional fairness in classification tasks. Our method capitalizes on the hierarchical structure inherent to intersectionality, by viewing groups as intersections of their parent categories. This perspective allows us to augment data for smaller groups by learning a transformation function that combines data from these parent groups. Our empirical analysis, conducted on four diverse datasets including both text and images, reveals that classifiers trained with this data augmentation approach achieve superior intersectional fairness and are more robust to "leveling down" when compared to methods optimizing traditional group fairness metrics.Lire moins >
Lire la suite >In this paper, we introduce a data augmentation approach specifically tailored to enhance intersectional fairness in classification tasks. Our method capitalizes on the hierarchical structure inherent to intersectionality, by viewing groups as intersections of their parent categories. This perspective allows us to augment data for smaller groups by learning a transformation function that combines data from these parent groups. Our empirical analysis, conducted on four diverse datasets including both text and images, reveals that classifiers trained with this data augmentation approach achieve superior intersectional fairness and are more robust to "leveling down" when compared to methods optimizing traditional group fairness metrics.Lire moins >
Langue :
Anglais
Collections :
Source :
Fichiers
- document
- Accès libre
- Accéder au document
- 2405.14521v1.pdf
- Accès libre
- Accéder au document
- 2405.14521
- Accès libre
- Accéder au document