Fairness-Aware Programming

Fairness-Aware Programming
复制标题

公平意识编程

DOI:
10.1145/3287560.3287588
复制
发表时间:
2019
期刊:
and Transparency
影响因子:
--
通讯作者:
Vinitsky, Samuel
Vinitsky, Samuel
中科院分区:
--
文献类型:
--
作者:
Albarghouthi, Aws;Vinitsky, Samuel

文献摘要

参考文献

被引文献

相似文献

越来越多的编程任务涉及到自动化和部署敏感的决策过程,这些决策过程可能对个人或群体产生不利影响。因此,自动化决策中的公平性问题已经成为一个重大问题,引起了跨学科的关注。在这项工作中,我们的目标是使公平性成为编程中的头等大事。具体来说,我们提出了公平感知编程,程序员可以在他们的代码中本地声明公平期望,并有一个运行时系统监控决策和报告违反公平的情况。我们提供了一种丰富而通用的规范语言,允许程序员从文献以及其他文献中指定一系列公平定义。当决策程序执行时,运行时维护所做决策的统计信息,并逐步检查是否违反了公平性定义,并向开发人员报告此类违规行为。这种方法的优点有两个方面:(i)在编程语言中启用公平性的声明性数学规范简化了检查公平性的过程,因为程序员不必为维护统计数据编写特别的代码。(ii)与现有的检查和确保公平性的技术相比,我们的方法监控了野外的决策程序,该程序可能运行在与分类器训练和测试的数据集不同的分布上。我们将我们提出的方法描述为Python编程语言中的库的实现,并说明其在算法公平性文献中的案例研究中的使用。
Increasingly, programming tasks involve automating and deploying sensitive decision-making processes that may have adverse impacts on individuals or groups of people. The issue of fairness in automated decision-making has thus become a major problem, attracting interdisciplinary attention. In this work, we aim to make fairness a first-class concern in programming. Specifically, we propose fairness-aware programming, where programmers can state fairness expectations natively in their code, and have a runtime system monitor decision-making and report violations of fairness.We present a rich and general specification language that allows a programmer to specify a range of fairness definitions from the literature, as well as others. As the decision-making program executes, the runtime maintains statistics on the decisions made and incrementally checks whether the fairness definitions have been violated, reporting such violations to the developer. The advantages of this approach are two fold: (i) Enabling declarative mathematical specifications of fairness in the programming language simplifies the process of checking fairness, as the programmer does not have to write ad hoc code for maintaining statistics. (ii) Compared to existing techniques for checking and ensuring fairness, our approach monitors a decision-making program in the wild, which may be running on a distribution that is unlike the dataset on which a classifier was trained and tested.We describe an implementation of our proposed methodology as a library in the Python programming language and illustrate its use on case studies from the algorithmic fairness literature.
DOI: --
发表时间: 2017
期刊: Neural Information Processing Systems
影响因子: --
作者:
Niki Kilbertus;Mateo Rojas;Giambattista Parascandolo;Moritz Hardt;D. Janzing;B. Scholkopf
通讯作者: B. Scholkopf
数据驱动系统中的代理非歧视
DOI: --
发表时间: 2017
期刊: arXiv.org
影响因子: --
作者:
Anupam Datta;Matt Fredrikson;Gihyuk Ko;Piotr (Peter) Mardziel;S. Sen
通讯作者: S. Sen
DOI: 10.1145/3133904
发表时间: 2017-10-01
影响因子: 1.8
作者:
Albarghouthi, Aws;D'Antoni, Loris;Nori, Aditya, V
通讯作者: Nori, Aditya, V
用于群体公平和高效机器学习的解耦分类器
DOI: --
发表时间: 2017
期刊: FAT
影响因子: --
作者:
C. Dwork;Nicole Immorlica;A. Kalai;Mark D. M. Leiserson
通讯作者: Mark D. M. Leiserson
DOI: 10.1007/978-3-319-54024-5_4
发表时间: 2017-01-01
期刊: TRANSPARENT DATA MINING FOR BIG AND SMALL DATA
影响因子: --
作者:
Datta, Anupam;Sen, Shayak;Zick, Yair
通讯作者: Zick, Yair