论文标题
公平 - 准确性帕累托前部
The Fairness-Accuracy Pareto Front
论文作者
论文摘要
算法公平旨在识别和纠正机器学习算法中偏见的来源。令人困惑的是，确保公平通常是以准确性为代价。我们在这项工作中提供了正式的工具，以核对算法公平的这种基本张力。具体来说，我们从多目标优化中使用帕累托最优性的概念，并寻求神经网络分类器的公平性 - 准确性帕累托前沿。我们证明，许多现有的算法公平方法正在执行所谓的线性标量方案，该方案在恢复帕累托最佳溶液方面有严重的限制。相反，我们采用了Chebyshev标量方案，该方案在理论上是优越的，并且与线性方案相比，在恢复Pareto最佳解决方案方面不再计算繁重。
Algorithmic fairness seeks to identify and correct sources of bias in machine learning algorithms. Confoundingly, ensuring fairness often comes at the cost of accuracy. We provide formal tools in this work for reconciling this fundamental tension in algorithm fairness. Specifically, we put to use the concept of Pareto optimality from multi-objective optimization and seek the fairness-accuracy Pareto front of a neural network classifier. We demonstrate that many existing algorithmic fairness methods are performing the so-called linear scalarization scheme which has severe limitations in recovering Pareto optimal solutions. We instead apply the Chebyshev scalarization scheme which is provably superior theoretically and no more computationally burdensome at recovering Pareto optimal solutions compared to the linear scheme.
