论文标题
私人人口统计数据公平学习
Fair Learning with Private Demographic Data
论文作者
论文摘要
在现实世界环境中，学习者很少能获得诸如种族的敏感属性，因为他们的收藏通常受到法律法规的限制。我们提供了一个计划，该计划使个人可以私下释放其敏感信息，同时仍允许任何下游实体学习非歧视性预测指标。我们展示了如何适应非歧视性学习者与私有化的受保护属性一起工作，从而为绩效提供了理论保证。最后，我们强调了该方法如何应用于仅适用于数据子集的受保护属性的设置中的学习公平预测变量。
Sensitive attributes such as race are rarely available to learners in real world settings as their collection is often restricted by laws and regulations. We give a scheme that allows individuals to release their sensitive information privately while still allowing any downstream entity to learn non-discriminatory predictors. We show how to adapt non-discriminatory learners to work with privatized protected attributes giving theoretical guarantees on performance. Finally, we highlight how the methodology could apply to learning fair predictors in settings where protected attributes are only available for a subset of the data.
