arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.10797cs.LGstat.ML
收藏

公平-准确帕累托前沿

The Fairness-Accuracy Pareto Front

University of Melbourne(墨尔本大学);University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校)

Susan Wei, Marc Niethammer

摘要:

算法公平性旨在识别和纠正机器学习算法中的偏差来源。令人困惑的是,确保公平往往是以牺牲准确性为代价的。在这项工作中,我们提供了正式的工具,协调算法公平性的基本紧张局势。具体地说,我们将多目标优化中的Pareto最优性概念引入到神经网络分类器中,寻求公平准确的Pareto前沿。我们证明,许多现有的算法公平性方法执行所谓的线性标量化方案,在恢复帕累托最优解有严重的局限性。相反,我们应用切比雪夫标量化方案,这是理论上证明优越的,并没有更多的计算负担,在恢复帕累托最优解相比,线性计划。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑