arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.05658cs.CYcs.AI
收藏

走向信息透明:多样性视角

Towards Algorithmic Transparency: A Diversity Perspective

University of Trento(特伦托大学);Open University of Cyprus(塞浦路斯开放大学);The University of Haifa(海法大学)

Fausto Giunchiglia, Jahna Otterbacher, Styliani Kleanthous, Khuyagbaatar Batsuren, Veronika Bogin, Tsvi Kuflik, Avital Shulner Tal

摘要:

随着算法系统和流程在社会中的作用越来越大,偏见的风险也越来越大,这可能导致对个人和社会群体的歧视。近年来,关于算法偏见的研究呈爆炸式增长,突出了偏差的问题以及算法透明度(AT)方面的潜在解决方案。透明度对于促进公平管理以及算法的可解释性很重要;然而,多样性的概念及其与偏见和透明度的关系在很大程度上被排除在讨论之外。我们反思了多样性和偏见之间的关系,认为多样性推动了透明度的需求。使用透视镜头,这需要多样性作为一个给定的,我们提出了一个概念框架来表征的问题和解决方案的AT空间,以帮助其在算法系统中的应用。使用我们的框架描述了三个研究领域的示例案例。

英文摘要:

As the role of algorithmic systems and processes increases in society, so does the risk of bias, which can result in discrimination against individuals and social groups. Research on algorithmic bias has exploded in recent years, highlighting both the problems of bias, and the potential solutions, in terms of algorithmic transparency (AT). Transparency is important for facilitating fairness management as well as explainability in algorithms; however, the concept of diversity, and its relationship to bias and transparency, has been largely left out of the discussion. We reflect on the relationship between diversity and bias, arguing that diversity drives the need for transparency. Using a perspective-taking lens, which takes diversity as a given, we propose a conceptual framework to characterize the problem and solution spaces of AT, to aid its application in algorithmic systems. Example cases from three research domains are described using our framework.

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。

↑