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：本文提出了一种新的框架，用于验证在偏差数据上训练的预测模型的公平性。该框架借鉴了不完整和不一致数据库的查询回答技术，将目标群体上预测模型的公平性查询问题形式化为一致性范围近似（CRA）。该框架利用数据收集过程和偏差数据的背景知识，在有或无目标群体有限统计数据的情况下，计算公平性查询的回答范围。通过CRA，该框架构建的预测模型能够在目标群体上保证公平性，无论训练过程中是否有外部数据可用。通过在真实数据上的评估，该框架的有效性得以展示，结果显示其显著优于现有的最先进方法。