arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2111.14348cs.LGcs.CY
收藏

一种基于因果关系的不公平边缘优先化和歧视消除方法

A Causal Approach for Unfair Edge Prioritization and Discrimination Removal

Robert Bosch Center for Data Science and Artificial Intelligence, IIT Madras(印度理工学院马德拉斯分校罗伯特·博世数据科学与人工智能中心);IIT Madras(印度理工学院马德拉斯分校)

Pavan Ravishankar, Pranshu Malviya, Balaraman Ravindran

摘要:

在执法等旨在减轻不公平现象的非理性约束环境中,在采取措施减轻现实世界中的不公平现象之前,必须优先考虑不公平现象的根源。与以前的作品,这只是作为一个警告,对可能的歧视和数据生成后的去偏置数据,这项工作提供了一个工具包,以减轻不公平的边缘优先级算法,在数据生成过程中的不公平,除了去偏置数据生成后,由歧视消除算法。我们假设一个非参数马尔可夫因果模型的数据生成过程的代表。从因果图中的敏感节点发出的边,如种族,被假定为不公平的来源。我们首先量化任何边X -> Y中的边流,这是由于沿X -> Y的X的特定值的影响而观察到Y的特定值的信念。然后,我们量化边缘不公平,制定一个非参数模型的边缘流。然后,我们证明,累积的不公平对敏感群体的决定,如种族的保释决定,是不存在的边缘不公平是缺席。我们证明了这一结果的非平凡的非参数模型设置时,累积的不公平不能表示在边缘不公平。然后,我们测量的潜力,以减轻累积不公平时,边缘不公平减少。基于这些测量,我们提出了不公平的边缘优先级算法,然后可以使用的政策制定者。我们还提出了歧视消除过程,消除偏见的数据分布,通过消除优化约束,指数增长的敏感属性和值的数量。大量的实验验证了用于量化上述措施的定理和规格。

英文摘要:

In budget-constrained settings aimed at mitigating unfairness, like law enforcement, it is essential to prioritize the sources of unfairness before taking measures to mitigate them in the real world. Unlike previous works, which only serve as a caution against possible discrimination and de-bias data after data generation, this work provides a toolkit to mitigate unfairness during data generation, given by the Unfair Edge Prioritization algorithm, in addition to de-biasing data after generation, given by the Discrimination Removal algorithm. We assume that a non-parametric Markovian causal model representative of the data generation procedure is given. The edges emanating from the sensitive nodes in the causal graph, such as race, are assumed to be the sources of unfairness. We first quantify Edge Flow in any edge X -> Y, which is the belief of observing a specific value of Y due to the influence of a specific value of X along X -> Y. We then quantify Edge Unfairness by formulating a non-parametric model in terms of edge flows. We then prove that cumulative unfairness towards sensitive groups in a decision, like race in a bail decision, is non-existent when edge unfairness is absent. We prove this result for the non-trivial non-parametric model setting when the cumulative unfairness cannot be expressed in terms of edge unfairness. We then measure the Potential to mitigate the Cumulative Unfairness when edge unfairness is decreased. Based on these measurements, we propose the Unfair Edge Prioritization algorithm that can then be used by policymakers. We also propose the Discrimination Removal Procedure that de-biases a data distribution by eliminating optimization constraints that grow exponentially in the number of sensitive attributes and values taken by them. Extensive experiments validate the theorem and specifications used for quantifying the above measures.

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。

↑