Fair Risk Control: A Generalized Framework for Calibrating Multi-group Fairness Risks
This work addresses fairness concerns for various applications in AI, though it is incremental as it builds on existing multicalibration concepts.
The paper tackles the problem of ensuring multi-group fairness in machine learning predictions by introducing a generalized framework for post-processing models, achieving fairness guarantees across diverse scenarios including image segmentation, hierarchical classification, and language models.
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.