Dutta Sanghamitra, Hamman Faisal
Department of Electrical and Computer Engineering, University of Maryland, College Park, MD 20742, USA.
Entropy (Basel). 2023 May 13;25(5):795. doi: 10.3390/e25050795.
Partial Information Decomposition (PID) is a body of work within information theory that allows one to quantify the information that several random variables provide about another random variable, either individually (unique information), redundantly (shared information), or only jointly (synergistic information). This review article aims to provide a survey of some recent and emerging applications of partial information decomposition in algorithmic fairness and explainability, which are of immense importance given the growing use of machine learning in high-stakes applications. For instance, PID, in conjunction with causality, has enabled the disentanglement of the non-exempt disparity which is the part of the overall disparity that is not due to critical job necessities. Similarly, in federated learning, PID has enabled the quantification of tradeoffs between local and global disparities. We introduce a taxonomy that highlights the role of PID in algorithmic fairness and explainability in three main avenues: (i) Quantifying the legally non-exempt disparity for auditing or training; (ii) Explaining contributions of various features or data points; and (iii) Formalizing tradeoffs among different disparities in federated learning. Lastly, we also review techniques for the estimation of PID measures, as well as discuss some challenges and future directions.
部分信息分解（PID）是信息论中的一个研究领域，它允许人们量化几个随机变量关于另一个随机变量所提供的信息，这些信息可以是单独提供的（独特信息）、冗余提供的（共享信息），或者仅通过联合提供的（协同信息）。这篇综述文章旨在概述部分信息分解在算法公平性和可解释性方面的一些最新及新兴应用，鉴于机器学习在高风险应用中的使用日益增加，这些应用极为重要。例如，PID与因果关系相结合，能够解开非豁免差异，即总体差异中并非源于关键工作需求的部分。同样，在联邦学习中，PID能够量化局部差异和全局差异之间的权衡。我们引入一种分类法，突出PID在算法公平性和可解释性方面在三个主要途径中的作用：（i）量化用于审计或训练的法律上非豁免差异；（ii）解释各种特征或数据点的贡献；以及（iii）形式化联邦学习中不同差异之间的权衡。最后，我们还回顾了估计PID度量的技术，并讨论了一些挑战和未来方向。
