FAI: A Normative Economic Approach to Fairness in AI

FAI：人工智能公平的规范经济方法

• 批准号: 2147187
• 负责人: Yiling Chen
• 金额: $ 56.03万
• 依托单位: Harvard University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-03-01 至 2025-02-28
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2147187&HistoricalAwards=false
• 关键词: FAI; Normative; Economic; Approach; Fairness

A vast body of work in algorithmic fairness is devoted to preventing artificial intelligence (AI) from exacerbating societal biases. The predominant viewpoints in this literature equates fairness with lack of bias or seeks to achieve some form of statistical parity between demographic groups. By contrast, this project pursues alternative approaches rooted in normative economics, the field that evaluates policies and programs by asking "what should be". The work is driven by two observations. First, fairness to individuals and groups can be realized according to people’s preferences represented in the form of utility functions. Second, traditional notions of algorithmic fairness may be at odds with welfare (the overall utility of groups), including the welfare of those groups the fairness criteria intend to protect. The goal of this project is to establish normative economic approaches as a central tool in the study of fairness in AI. Towards this end the team pursues two research questions. First, can the perspective of normative economics be reconciled with existing approaches to fairness in AI? Second, how can normative economics be drawn upon to rethink what fairness in AI should be? The project will integrate theoretical and algorithmic advances into real systems used to inform refugee resettlement decisions. The system will be examined from a fairness viewpoint, with the goal of ultimately ensuring fairness guarantees and welfare.The research plan includes two main directions based on previous work has shown that classifiers incorporating parity-based fairness criteria can be Pareto inefficient. That is, the welfare of all groups—including the protected group—would be higher under a classifier that is less fair. In the first direction, the project extends this observation to non-convex problems and then from in-processing to post-processing bias mitigation. The planned research will also study the interaction between multiple policy makers and its impact on social goals such as fairness and welfare. In the second direction, the project develops a new conceptualization in which classifiers are viewed as public resources or goods. This work then draws on ideas from fair division, a long-established branch of normative economics that defines and applies rigorous notions of fairness, and on the specific notion of the core. To put this idea into practice, there are several challenges that must be addressed: conditions for the existence of classifiers in the core, algorithms for their computation, and generalization from a training set.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.

算法公平性方面的大量工作致力于防止人工智能(AI)加剧社会偏见。这篇文献中的主要观点将公平等同于没有偏见，或者寻求在人口统计群体之间实现某种形式的统计平等。相比之下，这个项目寻求的是植根于规范经济学的替代方法，该领域通过询问“应该是什么”来评估政策和计划。这项工作是由两个观察推动的。首先，可以根据以效用函数形式表示的人们的偏好来实现对个人和群体的公平。其次，算法公平的传统概念可能与福利(群体的整体效用)不一致，包括公平标准打算保护的那些群体的福利。这个项目的目标是建立规范的经济学方法，作为研究人工智能公平的中心工具。为此，该团队提出了两个研究问题。首先，规范经济学的观点能否与人工智能中现有的公平方法相协调？其次，如何借鉴规范经济学来重新思考人工智能中的公平应该是什么？该项目将把理论和算法方面的进展纳入实际系统，以便为难民重新安置决定提供信息。该系统将从公平的角度进行审查，最终目标是确保公平保证和福利。研究计划包括两个主要方向，基于先前的工作表明，包含基于奇偶性的公平标准的分类器可能是帕累托低效的。也就是说，在一个不太公平的分类器下，所有群体--包括受保护群体--的福利会更高。在第一个方向上，该项目将这一观察扩展到非凸问题，然后从处理中到处理后的偏差缓解。这项计划中的研究还将研究多个政策制定者之间的互动及其对公平和福利等社会目标的影响。在第二个方向上，该项目发展了一种新的概念，将量词视为公共资源或公共物品。然后，这项工作借鉴了公平分工的思想，公平分工是规范经济学的一个由来已久的分支，它定义并应用了严格的公平概念，以及核心的具体概念。要将这一想法付诸实践，必须解决几个挑战：核心中分类器的存在条件，它们的计算算法，以及从训练集进行泛化。这一奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Learning When to Advise Human Decision Makers

• DOI: 10.48550/arxiv.2209.13578
• 发表时间: 2022-09
• 作者: Gali Noti;Yiling Chen

Now We're Talking: Better Deliberation Groups through Submodular Optimization

现在我们正在谈论：通过子模块优化更好的审议小组

• 发表时间: 2023
• 期刊: AAAI Conference on Artificial Intelligence
• 作者: Jake Barrett;Y. Gal;Paul Gölz;Rose M. Hong;Ariel D. Procaccia
• 通讯作者: Ariel D. Procaccia

Welfare-Maximizing Pooled Testing

• DOI: 10.48550/arxiv.2206.10660
• 发表时间: 2022-06
• 期刊: Proceedings of the 24th ACM Conference on Economics and Computation
• 作者: Edwin Lock;Francisco Javier Marmolejo-Cossío;Evi Micha;Ariel D. Procaccia

Is Sortition Both Representative and Fair?

抽签是否具有代表性和公平性？

• 发表时间: 2022
• 期刊: NeurIPS
• 作者: Soroush Ebadian, Gregory Kehne

Dynamic Placement in Refugee Resettlement

难民安置中的动态安置

• 发表时间: 2023
• 期刊: Operations research
• 影响因子: 2.7
• 作者: Narges Ahani, Paul Gölz