Fair Risk Control: A Generalized Framework for Calibrating Multi-group Fairness Risks
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917656450301952 |
|---|---|
| author | Zhang, Lujing Roth, Aaron Zhang, Linjun |
| author_facet | Zhang, Lujing Roth, Aaron Zhang, Linjun |
| contents | This paper introduces a framework for post-processing machine learning models so that their predictions satisfy multi-group fairness guarantees. Based on the celebrated notion of multicalibration, we introduce $(\mathbf{s},\mathcal{G}, α)-$GMC (Generalized Multi-Dimensional Multicalibration) for multi-dimensional mappings $\mathbf{s}$, constraint set $\mathcal{G}$, and a pre-specified threshold level $α$. We propose associated algorithms to achieve this notion in general settings. This framework is then applied to diverse scenarios encompassing different fairness concerns, including false negative rate control in image segmentation, prediction set conditional uncertainty quantification in hierarchical classification, and de-biased text generation in language models. We conduct numerical studies on several datasets and tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_02225 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fair Risk Control: A Generalized Framework for Calibrating Multi-group Fairness Risks Zhang, Lujing Roth, Aaron Zhang, Linjun Machine Learning Artificial Intelligence Computers and Society Methodology This paper introduces a framework for post-processing machine learning models so that their predictions satisfy multi-group fairness guarantees. Based on the celebrated notion of multicalibration, we introduce $(\mathbf{s},\mathcal{G}, α)-$GMC (Generalized Multi-Dimensional Multicalibration) for multi-dimensional mappings $\mathbf{s}$, constraint set $\mathcal{G}$, and a pre-specified threshold level $α$. We propose associated algorithms to achieve this notion in general settings. This framework is then applied to diverse scenarios encompassing different fairness concerns, including false negative rate control in image segmentation, prediction set conditional uncertainty quantification in hierarchical classification, and de-biased text generation in language models. We conduct numerical studies on several datasets and tasks. |
| title | Fair Risk Control: A Generalized Framework for Calibrating Multi-group Fairness Risks |
| topic | Machine Learning Artificial Intelligence Computers and Society Methodology |
| url | https://arxiv.org/abs/2405.02225 |