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.

本文研究通过个人隐私保护的方式，实现对受保护属性的学习，在使用中不产生歧视，同时在受保护属性只在数据子集中存在的情况下，实现公平预测模型的学习。

使用隐私人口统计数据进行公正学习

Fair Learning with Private Demographic Data

Automated decision making systems are increasingly being used in real-world
applications. In these systems for the most part, the decision rules are
derived by minimizing the training error on the available historical data.
Therefore, if there is a bias related to a sensitive attribute such as gender,
race, religion, etc. in the data, say, due to cultural/historical
discriminatory practices against a certain demographic, the system could
continue discrimination in decisions by including the said bias in its decision
rule. We present an information theoretic framework for designing fair
predictors from data, which aim to prevent discrimination against a specified
sensitive attribute in a supervised learning setting. We use equalized odds as
the criterion for discrimination, which demands that the prediction should be
independent of the protected attribute conditioned on the actual label. To
ensure fairness and generalization simultaneously, we compress the data to an
auxiliary variable, which is used for the prediction task. This auxiliary
variable is chosen such that it is decontaminated from the discriminatory
attribute in the sense of equalized odds. The final predictor is obtained by
applying a Bayesian decision rule to the auxiliary variable.

研究提出了一个信息理论框架来设计公平的预测器，以在监督学习环境中防止对指定敏感属性的歧视。使用平等的机会作为歧视标准，这要求在实际标签的条件下，预测应独立于受保护属性。同时确保公平和泛化，将数据压缩到辅助变量，再通过贝叶斯决策规则得到最终预测器。