arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.06920cs.AIcs.HC
收藏

正确对待公平:为从业者提供一个机会

Getting Fairness Right: Towards a Toolbox for Practitioners

AXA, REV Research(安盛REV研究中心)

Boris Ruf, Chaouki Boutharouite, Marcin Detyniecki

摘要:

人工智能系统无意中嵌入和复制偏见的潜在风险已经引起了机器学习从业者和整个社会的关注。随着政策制定者愿意制定算法和人工智能技术的标准,如何完善现有监管以强制执行自动化系统做出的决策是公平和非歧视性的问题再次变得至关重要。与此同时,研究人员已经证明,现有的各种公平性指标在统计上是相互排斥的,正确的选择主要取决于用例和公平性的定义。认识到实现公平人工智能的解决方案不是纯粹的数学,而是需要利益相关者承诺定义所需的公平性,本文建议起草一个工具箱,帮助从业者确保公平的人工智能实践。该工具箱旨在根据应用程序的性质和可用的训练数据,以及法律要求和伦理、哲学和文化层面,确定最适当的公平目标。这种方法试图构建公平性度量的复杂景观,因此,使非技术人员更容易获得不同的可用选项。在事实证明缺乏公平人工智能的银弹解决方案的情况下,这个工具箱旨在根据当地情况产生最公平的人工智能系统。

英文摘要:

The potential risk of AI systems unintentionally embedding and reproducing bias has attracted the attention of machine learning practitioners and society at large. As policy makers are willing to set the standards of algorithms and AI techniques, the issue on how to refine existing regulation, in order to enforce that decisions made by automated systems are fair and non-discriminatory, is again critical. Meanwhile, researchers have demonstrated that the various existing metrics for fairness are statistically mutually exclusive and the right choice mostly depends on the use case and the definition of fairness. Recognizing that the solutions for implementing fair AI are not purely mathematical but require the commitments of the stakeholders to define the desired nature of fairness, this paper proposes to draft a toolbox which helps practitioners to ensure fair AI practices. Based on the nature of the application and the available training data, but also on legal requirements and ethical, philosophical and cultural dimensions, the toolbox aims to identify the most appropriate fairness objective. This approach attempts to structure the complex landscape of fairness metrics and, therefore, makes the different available options more accessible to non-technical people. In the proven absence of a silver bullet solution for fair AI, this toolbox intends to produce the fairest AI systems possible with respect to their local context.

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。

↑