We propose an analysis in fair learning that preserves the utility of the data while reducing prediction disparities under the criteria of group sufficiency. We focus on the scenario where the data contains multiple or even many subgroups, each with limited number of samples. As a result, we present a principled method for learning a fair predictor for all subgroups via formulating it as a bilevel objective. Specifically, the subgroup specific predictors are learned in the lower-level through a small amount of data and the fair predictor. In the upper-level, the fair predictor is updated to be close to all subgroup specific predictors. We further prove that such a bilevel objective can effectively control the group sufficiency and generalization error. We evaluate the proposed framework on real-world datasets. Empirical evidence suggests the consistently improved fair predictions, as well as the comparable accuracy to the baselines.
翻译:我们建议进行公平学习分析,保留数据的效用,同时根据群体充足性标准减少预测差异。我们侧重于数据包含多个或甚至多个分组的情景,每个分组的样本数量有限。结果,我们提出了一个原则方法,通过将所有分组作为一个双级目标,为所有分组学习公平预测器。具体地说,分组特定预测器是通过少量数据和公平预测器在较低层次学习的。在较高层次,公平预测器被更新,接近所有分组特定预测器。我们进一步证明,这种双级目标能够有效控制小组的充足性和普遍性错误。我们评估了真实世界数据集的拟议框架。经验证据表明,公平预测不断改进,与基线相近。