Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.14521 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910457827164160 |
|---|---|
| author | Maheshwari, Gaurav Bellet, Aurélien Denis, Pascal Keller, Mikaela |
| author_facet | Maheshwari, Gaurav Bellet, Aurélien Denis, Pascal Keller, Mikaela |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_14521 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Synthetic Data Generation for Intersectional Fairness by Leveraging Hierarchical Group Structure Maheshwari, Gaurav Bellet, Aurélien Denis, Pascal Keller, Mikaela Machine Learning Computation and Language 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. |
| title | Synthetic Data Generation for Intersectional Fairness by Leveraging Hierarchical Group Structure |
| topic | Machine Learning Computation and Language |
| url | https://arxiv.org/abs/2405.14521 |