arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.08453cs.AIcs.HC
收藏

走向AI中的正确公平

Towards the Right Kind of Fairness in AI

AXA GO, AI Research(安盛GO人工智能研究院)

Boris Ruf, Marcin Detyniecki

摘要:

公平是一个正义的概念。存在各种定义,其中一些相互冲突。在没有一个统一接受的公平概念的情况下,为特定情况选择正确的公平一直是人类历史上的一个中心问题。当谈到在人工智能系统中实现可持续的公平性时,这个老问题再次发挥了关键作用:如何为特定应用确定最合适的公平性度量?答案往往是一个背景问题,最佳选择取决于道德标准和法律要求。由于目前关于这一主题的道德准则相当笼统,我们的目标是通过本文件提供更多的实践指导。因此,我们首先构建现有公平性指标的复杂景观,并通过示例解释不同的选项。此外,我们提出了“公平指南针”,这是一个工具,正式的选择过程,并确定最合适的公平定义为一个给定的系统一个简单,直接的程序。因为这个过程还允许记录各自的决定背后的推理,我们认为,这种方法可以帮助建立信任,通过解释和证明实施的公平性从用户。

英文摘要:

Fairness is a concept of justice. Various definitions exist, some of them conflicting with each other. In the absence of an uniformly accepted notion of fairness, choosing the right kind for a specific situation has always been a central issue in human history. When it comes to implementing sustainable fairness in artificial intelligence systems, this old question plays a key role once again: How to identify the most appropriate fairness metric for a particular application? The answer is often a matter of context, and the best choice depends on ethical standards and legal requirements. Since ethics guidelines on this topic are kept rather general for now, we aim to provide more hands-on guidance with this document. Therefore, we first structure the complex landscape of existing fairness metrics and explain the different options by example. Furthermore, we propose the "Fairness Compass", a tool which formalises the selection process and makes identifying the most appropriate fairness definition for a given system a simple, straightforward procedure. Because this process also allows to document the reasoning behind the respective decisions, we argue that this approach can help to build trust from the user through explaining and justifying the implemented fairness.

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。

↑