本文介绍了一个新颖的框架，用于解决机器学习模型中的公平性问题，特别是针对年龄或性别等连续受保护属性。所提出的方法使用路径特定偏导数来形式化公平性标准，扩展了现有的因果公式。它还提出了一种调优算法，旨在构建公平的预测器或在无法实现完美公平时管理不同公平性指标之间的权衡。 AI
影响 为在机器学习模型中实现因果公平性引入了新的理论框架和算法，特别是针对连续受保护属性。
排序理由 这是一篇发表在arXiv上的研究论文，详细介绍了机器学习中因果公平性的新理论框架和算法。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.05882v1 Announce Type: cross Abstract: Artificial-intelligence systems are becoming ubiquitous in society, yet their predictions typically inherit biases with respect to protected attributes such as race, gender, or age. Classical fairness notions, most notably Statist…
Artificial-intelligence systems are becoming ubiquitous in society, yet their predictions typically inherit biases with respect to protected attributes such as race, gender, or age. Classical fairness notions, most notably Statistical Parity (SP), demand that predictions be indep…