Configurable Fairness: Direct Optimization of Parity Metrics via Vision-Language Models

TL;DR

This paper introduces a method to directly optimize fairness metrics in image recognition models using vision-language models, improving parity-based fairness without needing group labels.

Contribution

It presents a novel approach that formulates loss functions linked to fairness metrics, enabling direct fairness optimization without relying on group annotations.

Findings

Significant improvement in fairness metrics across datasets.

Outperforms existing methods in fairness criteria.

Flexible optimization for different fairness objectives.

Abstract

Performance disparities of image recognition across demographic groups are known to exist in deep learning-based models, due to imbalanced group representations or spurious correlation between group and target labels. Previous work has addressed such challenges without relying on expensive group labels, typically by upweighting high-loss samples or balancing discovered clusters. However, these heuristic strategies lack direct connection to specific fairness metrics and cannot guarantee optimization of parity-based criteria like equal opportunity, which ensures equal chance to receive positive outcomes across groups. In this work, we propose a novel paradigm that directly optimizes parity-based fairness metrics through specifically designed training objectives, without requiring group labels. We leverage vision-language models to analyze sensitive attribute relevancy for individual samples, then formulate loss functions that mathematically connect to each target fairness metric. This enables flexible optimization of different fairness criteria based on application needs. Experiments on multiple image classification datasets show that our metric-specific approach significantly improves parity-based fairness criteria and outperforms existing methods.