arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1710.04394cs.LG
收藏

可证明的公平代表

Provably Fair Representations

The Australian National University(澳大利亚国立大学);CSIRO Data61(澳大利亚联邦科学与工业研究组织 Data61)

Daniel McNamara, Cheng Soon Ong, Robert C. Williamson

摘要:

机器学习系统越来越多地用于做出有关人们生活的决定,例如是否向某人提供贷款或是否面试某人的工作。这使得人们对使这种机器学习系统公平产生了相当大的兴趣。一种方法是变换算法所使用的输入数据。这可以通过在将每个输入数据点用于训练或测试之前使其通过表示函数来实现。从数据中学习这种表示函数的技术在经验上是成功的,但通常缺乏理论上的公平性保证。我们表明,它是可以证明,一个代表功能是公平的,根据共同的措施,群体和个人的公平性,以及有用的目标任务。这些可证明的属性可以用于涉及数据生产者、数据用户和数据监管者的治理模型中,其中公平性和目标任务效用之间存在关注点的分离,以确保透明度并防止不正当的激励。我们正式定义的“不信任的成本”使用这个模型相比,有一个单一的受信任方的设置,并提供在特定情况下,这个成本的界限。我们提出了一种实用的方法来学习公平表示函数,并将其应用于金融和刑事司法数据集。我们评估的公平性和实用性,这些代表性的功能,我们的理论结果的动机措施。

英文摘要:

Machine learning systems are increasingly used to make decisions about people's lives, such as whether to give someone a loan or whether to interview someone for a job. This has led to considerable interest in making such machine learning systems fair. One approach is to transform the input data used by the algorithm. This can be achieved by passing each input data point through a representation function prior to its use in training or testing. Techniques for learning such representation functions from data have been successful empirically, but typically lack theoretical fairness guarantees. We show that it is possible to prove that a representation function is fair according to common measures of both group and individual fairness, as well as useful with respect to a target task. These provable properties can be used in a governance model involving a data producer, a data user and a data regulator, where there is a separation of concerns between fairness and target task utility to ensure transparency and prevent perverse incentives. We formally define the 'cost of mistrust' of using this model compared to the setting where there is a single trusted party, and provide bounds on this cost in particular cases. We present a practical approach to learning fair representation functions and apply it to financial and criminal justice datasets. We evaluate the fairness and utility of these representation functions using measures motivated by our theoretical results.

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。

↑