This paper proposes a novel framework for certifying the fairness of predictive models trained on biased data. It draws from query answering for incomplete and inconsistent databases to formulate the problem of consistent range approximation (CRA) of fairness queries for a predictive model on a target population. The framework employs background knowledge of the data collection process and biased data, working with or without limited statistics about the target population, to compute a range of answers for fairness queries. Using CRA, the framework builds predictive models that are certifiably fair on the target population, regardless of the availability of external data during training. The framework's efficacy is demonstrated through evaluations on real data, showing substantial improvement over existing state-of-the-art methods.

翻译：本文提出了一种新颖的框架，用于验证在偏斜数据上训练的预测模型的公平性。该框架借鉴了针对不完整和不一致数据库的查询回答技术，将目标人群上预测模型公平性查询的一致性范围近似（CRA）问题形式化。该框架利用数据收集过程和偏斜数据的背景知识，无论是否使用关于目标人群的有限统计数据，都能计算公平性查询的答案范围。通过CRA，该框架构建的预测模型可以在目标人群上被证明公平，无论训练过程中是否有外部数据的支持。通过在真实数据上的评估，该框架的有效性得到了验证，显示出相较于现有最先进方法的显著改进。