论文标题
Fairnnnnnnnnnnnnnnnnnne of for公平决策的公平代表
FairNN- Conjoint Learning of Fair Representations for Fair Decisions
论文作者
论文摘要
在本文中，我们提出了Fairnn的神经网络，该神经网络对公平感知学习执行联合特征表示和分类。我们的方法优化了多目标损耗函数，在该函数中，（a）通过抑制受保护的属性（b）来学习公平表示，通过使重建损失最小化来维护信息内容，并且（c）允许通过公平地求解分类任务，通过使分类误差最小化分类任务，并尊重基于均衡的赔率公平性。我们对各种数据集的实验表明，这种联合方法在表示或监督学习中对不公平性的单独处理优越。此外，我们的正规化器可以自适应加权以平衡损失函数的不同组成部分，从而为联合公平表示学习和决策做出非常一般的框架。
In this paper, we propose FairNN a neural network that performs joint feature representation and classification for fairness-aware learning. Our approach optimizes a multi-objective loss function in which (a) learns a fair representation by suppressing protected attributes (b) maintains the information content by minimizing a reconstruction loss and (c) allows for solving a classification task in a fair manner by minimizing the classification error and respecting the equalized odds-based fairness regularized. Our experiments on a variety of datasets demonstrate that such a joint approach is superior to separate treatment of unfairness in representation learning or supervised learning. Additionally, our regularizers can be adaptively weighted to balance the different components of the loss function, thus allowing for a very general framework for conjoint fair representation learning and decision making.
