利用偏信息分解对群体公平性权衡的统一视角
A Unified View of Group Fairness Tradeoffs Using Partial Information Decomposition
AI总结：
本文利用偏信息分解（PID）揭示统计 parity、均等机会与预测 parity 三种群体公平性度量的精确关系、重叠与权衡区域，并以数值模拟验证。
摘要：
本文针对机器学习中主要的群体公平性概念，即统计 parity、均等机会和预测 parity，之间的关系提出了一种新颖的信息论视角。众所周知，同时满足这三种公平性概念通常是不可能的，这促使从业者采用近似公平性解决方案，而非严格满足这些定义。然而，对它们相互关系的全面分析，尤其是在它们未被精确满足时，仍基本未被探索。我们的主要贡献在于利用信息论中称为偏信息分解（PID）的一系列工作，阐明这三种（不）公平性度量之间的精确关系。在本工作中，我们利用 PID 识别这三种（不）公平性度量重叠的细粒度区域，以及它们彼此不一致从而导致潜在权衡的区域。我们还加入了数值模拟以补充我们的结果。
英文摘要：
This paper introduces a novel information-theoretic perspective on the relationship between prominent group fairness notions in machine learning, namely statistical parity, equalized odds, and predictive parity. It is well known that simultaneous satisfiability of these three fairness notions is usually impossible, motivating practitioners to resort to approximate fairness solutions rather than stringent satisfiability of these definitions. However, a comprehensive analysis of their interrelations, particularly when they are not exactly satisfied, remains largely unexplored. Our main contribution lies in elucidating an exact relationship between these three measures of (un)fairness by leveraging a body of work in information theory called partial information decomposition (PID). In this work, we leverage PID to identify the granular regions where these three measures of (un)fairness overlap and where they disagree with each other leading to potential tradeoffs. We also include numerical simulations to complement our results.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
