FAI: Identifying, Measuring, and Mitigating Fairness Issues in AI

FAI：识别、衡量和缓解人工智能中的公平问题

• 批准号: 1939728
• 负责人: Christopher Clifton
• 金额: $ 21.69万
• 依托单位: Purdue University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-01-01 至 2021-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1939728&HistoricalAwards=false
• 关键词: FAI; Identifying; Measuring; Mitigating; Fairness

Bias and Discrimination in Artificial Intelligence (AI) has been receiving increasing attention. Unfortunately, the positive concept Fair AI is difficult to define. For example, it is hard to distinguish between (desired) personalization and (undesired) bias. These differences often depend on context, such as the use of gender or ethnicity in making a medical diagnosis vs. using the same attributes in determining if insurance should cover a medical procedure. This is particularly difficult as AI systems are used in new contexts, enabling products and services that have not been seen before and for which societal concepts of fairness are not yet established. This multidisciplinary project will construct a framework and taxonomy for understanding fairness in societal contexts. Human-computer interaction methods will be developed to learn perceptions of fairness based on human interaction with AI systems. Automated methods will be developed to relate these perceptions to the framework, enabling developers (and eventually automated AI systems) to respond to and correct issues perceived by users of the systems.This exploratory project will develop a taxonomy incorporating concepts of Aristotelian fairness (distributive vs. corrective justice) and Rawlsian fairness (equality of rights and opportunities). A formal literature survey will be used to establish a framework for societal contexts of fairness and how they relate to the Taxonomy. Experiments with perceptions of models both in isolation and in comparison will be used to evaluate situations where people perceive AI systems as fair or unfair. Tools will be developed to identify and explain fairness issues in terms of the taxonomy, based on the elicited perceptions and societal context of the system. While beyond the scope of this project, the outcome of these tools could potentially be used to automatically adjust AI systems to reduce unfairness.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

人工智能（AI）中的偏见和歧视越来越受到人们的关注。不幸的是，公平AI的积极概念很难定义。例如，很难区分（期望的）个性化和（不期望的）偏见。这些差异通常取决于背景，例如在进行医疗诊断时使用性别或种族，而在确定保险是否应涵盖医疗程序时使用相同的属性。这尤其困难，因为人工智能系统被用于新的环境中，使以前从未见过的产品和服务成为可能，而社会公平概念尚未建立。这个多学科的项目将构建一个框架和分类，以理解社会背景下的公平。将开发人机交互方法，以基于人类与人工智能系统的交互来学习公平感。将开发自动化方法，将这些感知与框架联系起来，使开发人员（最终是自动化人工智能系统）能够响应和纠正系统用户感知的问题。这个探索性项目将开发一个分类法，将亚里士多德的公平（分配与矫正正义）和罗尔斯的公平（权利和机会平等）概念结合起来。一个正式的文献调查将被用来建立一个框架的社会背景下的公平性，以及它们如何与分类。对模型进行单独和比较的实验将用于评估人们认为AI系统公平或不公平的情况。将开发工具，以确定和解释公平问题的分类，根据引发的看法和社会背景的系统。虽然超出了该项目的范围，但这些工具的结果可能会被用于自动调整人工智能系统，以减少不公平。该奖项反映了NSF的法定使命，并被认为值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估来支持。

项目成果

Rethinking Fairness: An Interdisciplinary Survey of Critiques of Hegemonic ML Fairness Approaches

• DOI: 10.1613/jair.1.13196
• 发表时间: 2022-05
• 期刊: ArXiv
• 作者: Lindsay Weinberg

JupyterLab in Retrograde: Contextual Notifications That Highlight Fairness and Bias Issues for Data Scientists

JupyterLab 逆行：强调数据科学家公平性和偏见问题的上下文通知

• 发表时间: 2024
• 期刊: Proceedings of the CHI Conference on Human Factors in Computing Systems
• 作者: Harrison, Galen;Bryson, Kevin;Bamba, Ahmad Emmanuel;Dovichi, Luca;Binion, Aleksander Herrmann;Borem, Arthur;Ur, Blase
• 通讯作者: Ur, Blase

Fairness as Equal Concession: Critical Remarks on Fair AI

公平即平等让步：对公平人工智能的批评

• DOI: 10.1007/s11948-021-00348-z
• 发表时间: 2021
• 期刊: Science and Engineering Ethics
• 影响因子: 3.7
• 作者: van Nood, Ryan;Yeomans, Christopher
• 通讯作者: Yeomans, Christopher

Explaining Why: How Instructions and User Interfaces Impact Annotator Rationales When Labeling Text Data

• DOI: 10.18653/v1/2022.naacl-main.38
• 发表时间: 2022
• 期刊: Nature Communications
• 影响因子: 16.6
• 作者: Jamar L. Sullivan;Will Brackenbury;Andrew McNut;K. Bryson;Kwam Byll;Yuxin Chen;M. Littman;Chenhao Tan;Blase Ur

Taking Data Out of Context to Hyper-Personalize Ads: Crowdworkers' Privacy Perceptions and Decisions to Disclose Private Information

断章取义地制作超个性化广告：众包工作者的隐私认知和披露私人信息的决定

• DOI: 10.1145/3313831.3376415
• 发表时间: 2020
• 期刊: CHI '20: Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems
• 作者: Hanson, Julia;Wei, Miranda;Veys, Sophie;Kugler, Matthew;Strahilevitz, Lior;Ur, Blase
• 通讯作者: Ur, Blase