论文标题
通过对手重新持续学习而无需人口统计学的公平性
Fairness without Demographics through Adversarially Reweighted Learning
论文作者
论文摘要
以前的许多机器学习（ML）公平文献都假设数据集中存在受保护的特征，例如种族和性别，并依靠它们来缓解公平关注。但是，在实践中，隐私和法规等因素通常会排除受保护特征的收集，或者用于培训或推理的使用，严重限制了传统公平研究的适用性。因此，我们问：当我们甚至不知道受保护的小组成员身份时，我们如何培训ML模型以提高公平性？在这项工作中，我们通过提出对手重新加权学习（ARL）来解决这个问题。特别是，我们假设非保护特征和任务标签对于识别公平性问题很有价值，并且可以用来共同培训一种对抗性重新加权方法以改善公平性。我们的结果表明，{arl}改善了Rawlsian Max-min公平性，对多个数据集中最坏的受保护组的AUC显着改善，表现优于最先进的替代方案。
Much of the previous machine learning (ML) fairness literature assumes that protected features such as race and sex are present in the dataset, and relies upon them to mitigate fairness concerns. However, in practice factors like privacy and regulation often preclude the collection of protected features, or their use for training or inference, severely limiting the applicability of traditional fairness research. Therefore we ask: How can we train an ML model to improve fairness when we do not even know the protected group memberships? In this work we address this problem by proposing Adversarially Reweighted Learning (ARL). In particular, we hypothesize that non-protected features and task labels are valuable for identifying fairness issues, and can be used to co-train an adversarial reweighting approach for improving fairness. Our results show that {ARL} improves Rawlsian Max-Min fairness, with notable AUC improvements for worst-case protected groups in multiple datasets, outperforming state-of-the-art alternatives.
