Counterfactual Fairness: Unidentification, Bound and Algorithm
Counterfactual Fairness: Unidentification, Bound and Algorithm
复制标题
DOI：
10.24963/ijcai.2019/199
复制
发表时间：
2019-08
期刊：
影响因子：
--
通讯作者：
Yongkai Wu;Lu Zhang;Xintao Wu
中科院分区：
文献类型：
--
作者：
Yongkai Wu;Lu Zhang;Xintao Wu
公平意识学习研究的是建立满足公平要求的机器学习模型的问题。反事实公平是从珀尔的因果模型衍生而来的公平概念，该模型认为，如果对于特定的个人或群体，该模型在现实世界中的预测与该个人(S)属于不同人口群体的反事实世界中的预测相同，则该模型是公平的。然而，反事实公平性的一个固有局限性是，由于反事实数量的不可辨识性，在某些情况下，它不能从观测数据中唯一地量化。在本文中，我们通过对不可识别的反事实数量进行数学界定来解决这一局限性，并开发了一个理论上合理的构造反事实公平分类器的算法。我们使用合成数据集和真实数据集在实验中对我们的方法进行了评估，并与现有方法进行了比较。实验结果验证了我们的理论，说明了我们方法的有效性。
Fairness-aware learning studies the problem of building machine learning models that are subject to fairness requirements. Counterfactual fairness is a notion of fairness derived from Pearl's causal model, which considers a model is fair if for a particular individual or group its prediction in the real world is the same as that in the counterfactual world where the individual(s) had belonged to a different demographic group. However, an inherent limitation of counterfactual fairness is that it cannot be uniquely quantified from the observational data in certain situations, due to the unidentifiability of the counterfactual quantity. In this paper, we address this limitation by mathematically bounding the unidentifiable counterfactual quantity, and develop a theoretically sound algorithm for constructing counterfactually fair classifiers. We evaluate our method in the experiments using both synthetic and real-world datasets, as well as compare with existing methods. The results validate our theory and show the effectiveness of our method.