We present a data-driven framework for learning fair universal representations (FUR) that guarantee statistical fairness for any learning task that may not be known a priori. Our framework leverages recent advances in adversarial learning to allow a data holder to learn representations in which a set of sensitive attributes are decoupled from the rest of the dataset. We formulate this as a constrained minimax game between an encoder and an adversary where the constraint ensures a measure of usefulness (utility) of the representation. The resulting problem is that of censoring, i.e., finding a representation that is least informative about the sensitive attributes given a utility constraint. For appropriately chosen adversarial loss functions, our censoring framework precisely clarifies the optimal adversarial strategy against strong information-theoretic adversaries; it also achieves the fairness measure of demographic parity for the resulting constrained representations. We evaluate the performance of our proposed framework on both synthetic and publicly available datasets. For these datasets, we use two tradeoff measures: censoring vs. representation fidelity and fairness vs. utility for downstream tasks, to amply demonstrate that multiple sensitive features can be effectively censored even as the resulting fair representations ensure accuracy for multiple downstream tasks.
翻译:我们提出了一个数据驱动框架,用于学习可能事先不为人知的公平普遍代表制(FUR),保证任何学习任务在统计上的公平性。我们的框架利用对抗性学习的最新进展,使数据持有人能够学习一套敏感属性与数据集其余部分脱钩的表示式。我们将此设计成一个在编码器和对手之间受到限制的小型游戏,其制约确保了代表制的效用(效用)的衡量。由此产生的问题在于审查,即找到对敏感属性了解最少的表示式,因为存在效用限制。对于适当选择的对抗性损失功能,我们的审查框架精确地澄清了针对强大信息理论对手的最佳对抗性战略;它还实现了对由此产生的限制表示式进行人口均等的公平衡量。我们评估了我们关于合成和公开提供数据集的拟议框架的性能。关于这些数据集,我们使用了两种权衡措施:审查对代表的忠诚和公平性与下游任务的实用性,以充分证明多重敏感特征可以有效地在下游审查,即使由此产生公平代表制,也确保了多重的准确性。