论文标题
确保超出培训数据的公平性
Ensuring Fairness Beyond the Training Data
论文作者
论文摘要
我们启动对训练分布扰动的合理分类器的研究。尽管最近取得了进展，但有关公平性的文献在很大程度上忽略了公平和强大的分类器的设计。在这项工作中，我们开发的分类器不仅在培训分布方面都是公平的，而且对于培训样本加权扰动的一类分布。我们制定了一个最小的目标函数，其目标是最大程度地减少分配强大的训练损失，同时，找到相对于一类分布的分类器。我们首先将这个问题减少到找到相对于分布类别的公平分类器。基于在线学习算法，我们开发了一种迭代算法，该算法可证明可以融合到这样一个公平而强大的解决方案。标准机器学习公平数据集的实验表明，与最先进的公平分类器相比，我们的分类器保留了公平性保证和测试准确性，并在测试集中进行大量扰动。此外，我们的实验表明，这种分类器的公平性稳健性和准确性之间存在固有的权衡。
We initiate the study of fair classifiers that are robust to perturbations in the training distribution. Despite recent progress, the literature on fairness has largely ignored the design of fair and robust classifiers. In this work, we develop classifiers that are fair not only with respect to the training distribution, but also for a class of distributions that are weighted perturbations of the training samples. We formulate a min-max objective function whose goal is to minimize a distributionally robust training loss, and at the same time, find a classifier that is fair with respect to a class of distributions. We first reduce this problem to finding a fair classifier that is robust with respect to the class of distributions. Based on online learning algorithm, we develop an iterative algorithm that provably converges to such a fair and robust solution. Experiments on standard machine learning fairness datasets suggest that, compared to the state-of-the-art fair classifiers, our classifier retains fairness guarantees and test accuracy for a large class of perturbations on the test set. Furthermore, our experiments show that there is an inherent trade-off between fairness robustness and accuracy of such classifiers.
