Fairness is increasingly recognized as a critical component of machine learning systems. However, it is the underlying data on which these systems are trained that often reflect discrimination, suggesting a database repair problem. Existing treatments of fairness rely on statistical correlations that can be fooled by anomalies, such as Simpson's paradox. Proposals for causality-based definitions of fairness can correctly model some of these situations, but they rely on background knowledge of the underlying causal models. In this paper, we formalize the situation as a database repair problem, proving sufficient conditions for fair classifiers in terms of admissible variables as opposed to a complete causal model. We show that these conditions correctly capture subtle fairness violations. We then use these conditions as the basis for database repair algorithms that provide provable fairness guarantees about classifiers trained on their training labels. We demonstrate the effectiveness of our proposed techniques with experimental results.

中文翻译：

---

数据库修复符合算法公平

公平性越来越被认为是机器学习系统的关键组成部分。然而，正是这些系统被训练的基础数据往往反映了歧视，这表明存在数据库修复问题。现有的公平处理方法依赖于统计相关性，这些相关性可能会被异常所愚弄，例如辛普森悖论。基于因果关系的公平定义建议可以正确地模拟其中一些情况，但它们依赖于潜在因果模型的背景知识。在本文中，我们将这种情况形式化为数据库修复问题，根据可接受变量而不是完整的因果模型证明公平分类器的充分条件。我们表明，这些条件正确地捕获了微妙的公平违规行为。然后，我们将这些条件用作数据库修复算法的基础，这些算法为在其训练标签上训练的分类器提供可证明的公平性保证。我们用实验结果证明了我们提出的技术的有效性。