不使用性别等敏感属性也能减少算法歧视，且不影响预测准确率。
Reconsidering Fairness Through Unawareness From the Perspective of Model Multiplicity
- 不依赖敏感属性进行决策，仍可降低算法偏见
- 理论与实证均证明该方法不损害整体预测精度
- 适合高风险场景中追求公平性的实际应用
公平性通过无意识（FtU）主张：若在决策中不考虑群体身份，即可避免对特定人群的歧视。该观点长期受到机器学习领域的质疑，认为其不足以保障公平，且引入额外特征通常被认为能提升所有群体的预测准确率，因此认为FtU可能对所有群体不利。本文从模型多样性（Model Multiplicity）视角出发，通过理论和实证研究发现，FtU可在不降低准确率的前提下减少算法歧视。我们进一步展示了在真实应用场景中，采用FtU有助于部署更公平但不失效的政策。结果表明，在高风险情境下，应重新评估FtU的价值，且使用性别等受保护属性时需有明确合理依据。
原文摘要 · Abstract (English)
Fairness through Unawareness (FtU) describes the idea that discrimination against demographic groups can be avoided by not considering group membership in the decisions or predictions. This idea has long been criticized in the machine learning literature as not being sufficient to ensure fairness. In addition, the use of additional features is typically thought to increase the accuracy of the predictions for all groups, so that FtU is sometimes thought to be detrimental to all groups. In this paper, we show both theoretically and empirically that FtU can reduce algorithmic discrimination without necessarily reducing accuracy. We connect this insight with the literature on Model Multiplicity, to which we contribute with novel theoretical and empirical results. Furthermore, we illustrate how, in a real-life application, FtU can contribute to the deployment of more equitable policies without losing efficacy. Our findings suggest that FtU is worth considering in practical applications, particularly in high-risk scenarios, and that the use of protected attributes such as gender in predictive models should be accompanied by a clear and well-founded justification.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。