用混合整数优化实现多维度公平性，让AI决策更透明可信。
Intersectional Fairness via Mixed-Integer Optimization
- 基于混合整数优化构建统一框架，同时优化公平性与可解释性。
- 实证显示该方法能更精准识别最不公平的群体子集。
- 适合金融、医疗等需强监管的高风险领域使用。
人工智能在金融、医疗等高风险领域的应用，要求模型兼具公平性与透明性。尽管欧盟《人工智能法案》等监管框架要求消除偏见，但对偏见的定义仍保持模糊。基于现有研究，我们认为真正的公平必须关注受保护群体之间的交叉效应。本文提出一种统一框架，利用混合整数优化（MIO）训练具有交叉公平性和内在可解释性的分类器。我们证明了两种交叉公平性度量（MSD与SPSF）在检测最不公平子群方面等价，并通过实验证明，基于MIO的算法在识别偏见方面表现更优。所训练的分类器在保持高性能的同时，将交叉偏见控制在可接受阈值以下，为受监管行业及其他领域提供了稳健解决方案。
原文摘要 · Abstract (English)
The deployment of Artificial Intelligence in high-risk domains, such as finance and healthcare, necessitates models that are both fair and transparent. While regulatory frameworks, including the EU's AI Act, mandate bias mitigation, they are deliberately vague about the definition of bias. In line with existing research, we argue that true fairness requires addressing bias at the intersections of protected groups. We propose a unified framework that leverages Mixed-Integer Optimization (MIO) to train intersectionally fair and intrinsically interpretable classifiers. We prove the equivalence of two measures of intersectional fairness (MSD and SPSF) in detecting the most unfair subgroup and empirically demonstrate that our MIO-based algorithm improves performance in finding bias. We train high-performing, interpretable classifiers that bound intersectional bias below an acceptable threshold, offering a robust solution for regulated industries and beyond.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。