On Learning and Testing of Counterfactual Fairness through Data Preprocessing

• 成果类型: Article
• 署名作者: Chen, Haoyu; Lu, Wenbin; Song, Rui; Ghosh, Pulak
• 署名单位: North Carolina State University; Indian Institute of Management (IIM System); Indian Institute of Management Bangalore; Indian Institute of Management (IIM System); Indian Institute of Management Bangalore
• 刊物名称: JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
• ISSN/ISSBN: 0162-1459
• DOI: 10.1080/01621459.2023.2186885
• 发表日期: 2024
• 页码: 1286-1296
• 关键词: race

摘要

Machine learning has become more important in real-life decision-making but people are concerned about the ethical problems it may bring when used improperly. Recent work brings the discussion of machine learning fairness into the causal framework and elaborates on the concept of Counterfactual Fairness. In this paper, we develop the Fair Learning through dAta Preprocessing (FLAP) algorithm to learn counterfactually fair decisions from biased training data and formalize the conditions where different data preprocessing procedures should be used to guarantee counterfactual fairness. We also show that Counterfactual Fairness is equivalent to the conditional independence of the decisions and the sensitive attributes given the processed non-sensitive attributes, which enables us to detect discrimination in the original decision using the processed data. The performance of our algorithm is illustrated using simulated data and real-world applications.