arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.02474cs.LGcs.AIcs.CY
收藏

概率电路的公平性证明

Certifying Fairness of Probabilistic Circuits

University of California, Los Angeles(加州大学洛杉矶分校);Arizona State University(亚利桑那州立大学)

Nikil Roashan Selvam, Guy Van den Broeck, YooJung Choi

摘要:

随着越来越多地使用机器学习系统进行决策,有关此类系统的公平性的问题开始占据中心舞台。大多数关于算法公平性的现有工作都假设在预测时完全观察到特征,就像统计奇偶性和机会均等等流行概念一样。然而,这对于可以通过部分观察进行预测的模型来说是不够的,因为我们可能会错过偏差模式并错误地证明模型是公平的。为了解决这个问题,最近引入的公平性概念询问模型是否表现出任何歧视模式,其中以(部分)特征观察为特征的个体仅通过披露一个或多个敏感属性(如性别和种族)来获得截然不同的决定。通过显式地解释部分观测,这提供了一个更细粒度的公平性概念。在本文中,我们提出了一个算法来搜索歧视模式的一般类的概率模型,即概率电路。以前,这样的算法仅限于朴素贝叶斯分类器,使强大的独立性假设;相比之下,概率电路提供了一个统一的框架,范围广泛的易处理的概率模型,甚至可以从某些类别的贝叶斯网络和概率程序编译,使我们的方法更广泛地适用。此外,对于不公平的模型,快速找到歧视模式并提取它们以获得更好的可解释性可能是有用的。因此,我们还提出了一种基于采样的方法来更有效地挖掘歧视模式,并引入了新的模式类别,如最小,最大和帕累托最优模式,可以有效地指数总结许多歧视模式

英文摘要:

With the increased use of machine learning systems for decision making, questions about the fairness properties of such systems start to take center stage. Most existing work on algorithmic fairness assume complete observation of features at prediction time, as is the case for popular notions like statistical parity and equal opportunity. However, this is not sufficient for models that can make predictions with partial observation as we could miss patterns of bias and incorrectly certify a model to be fair. To address this, a recently introduced notion of fairness asks whether the model exhibits any discrimination pattern, in which an individual characterized by (partial) feature observations, receives vastly different decisions merely by disclosing one or more sensitive attributes such as gender and race. By explicitly accounting for partial observations, this provides a much more fine-grained notion of fairness. In this paper, we propose an algorithm to search for discrimination patterns in a general class of probabilistic models, namely probabilistic circuits. Previously, such algorithms were limited to naive Bayes classifiers which make strong independence assumptions; by contrast, probabilistic circuits provide a unifying framework for a wide range of tractable probabilistic models and can even be compiled from certain classes of Bayesian networks and probabilistic programs, making our method much more broadly applicable. Furthermore, for an unfair model, it may be useful to quickly find discrimination patterns and distill them for better interpretability. As such, we also propose a sampling-based approach to more efficiently mine discrimination patterns, and introduce new classes of patterns such as minimal, maximal, and Pareto optimal patterns that can effectively summarize exponentially many discrimination patterns

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。

↑