FAI: FairGame: An Audit-Driven Game Theoretic Framework for Development and Certification of Fair AI

FAI：FairGame：用于公平人工智能开发和认证的审计驱动的博弈论框架

• 批准号: 1939677
• 负责人: Yevgeniy Vorobeychik
• 金额: $ 44.41万
• 依托单位: Washington 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 2023-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1939677&HistoricalAwards=false
• 关键词: FAI; FairGame; Audit; Driven; Game

The increasing impact of AI technologies on real applications has subjected these to unprecedented scrutiny. One of the major concerns is the extent to which these technologies reproduce or exacerbate inequity, with a number of high-profile examples, such as bias in recidivism prediction, illustrating the potential limitations of, and eroding trust in, AI. While approaches have emerged that aim to guarantee some form of fairness of AI systems, most are restricted to relatively simple prediction problems, without accounting for specific use cases of predictions. However, many practical uses of predictive models involve decisions that occur over time, and that are obtained by solving complex optimization problems. Moreover, few general approaches exist even for ascertaining equitable outcomes of dynamic decisions, let alone providing guidance for ensuring equity in such settings. To address these limitations, this project is developing a framework called FairGame for the development and certification of fair autonomous decision-making algorithms. This project will also develop new courses and course modules at Washington University, take a lead role in a new interdisciplinary program in Computational and Data Sciences, seek to inform policymakers and regulators about computational approaches to ensuring fairness, and work to broaden participation in computing through, for example, the Missouri Louis Stokes Alliance for Minority Participation.This project develops an audit-driven game theoretic framework for the development and certification of fair autonomous decision-making algorithms. FairGame features a decision module that computes a decision policy, and a pseudo-adversarial auditor providing feedback to the decision module about possible fairness violations, as well as providing fairness certification. The FairGame framework conceptually resembles the well-known actor-critic methods in reinforcement learning; however, unlike actor-critic methods, it enforces that the auditor has only query access to the policy, and, conversely, the decision module can only query the auditor (which provides feedback on the decisions). Different notions of fairness and efficacy can be modeled as different types of two-player games between the decision module and the auditor. This project will study foundational issues in this framework, including (a) the extent to which (probabilistically) certifying fairness in a black-box setting is possible, (b) practical algorithms for auditing, (c) iterative approaches for ensuring fair-decisions given a black-box access to an auditor, including policy gradient methods and Bayesian optimization, and (d) appropriate fairness and efficacy criteria, and (e) whether these criteria can satisfy different regulatory models, such as a requirement of “meaningful information about the logic” or legally imposed requirements of nondiscrimination. The work will be informed by the real policy challenge of developing fair algorithms for provision of services to homeless households, and provide feedback in this domain to key stakeholders.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.

人工智能技术对实际应用的影响越来越大，这使得这些技术受到前所未有的审查，其中一个主要问题是这些技术在多大程度上再现或加剧了不平等，一些引人注目的例子，例如累犯预测的偏差，说明了这一点。尽管已经出现了旨在保证人工智能系统某种形式公平性的方法，但大多数方法仅限于相对简单的预测问题，而没有考虑到预测的具体用例。预测模型的使用涉及决策而且，即使是确定动态决策的公平结果，也很少有通用方法，更不用说为确保此类环境中的公平性提供指导了。为了解决这些限制，该项目正在开发。该项目还将在华盛顿大学开发新的课程和课程模块，在计算和数据科学的新跨学科项目中发挥主导作用，并寻求为政策制定者提供信息。和监管机构关于确保公平的计算方法，以及例如，通过密苏里州路易斯斯托克斯少数族裔参与联盟等机构，致力于扩大对计算的参与。该项目开发了一个审计驱动的博弈论框架，用于开发和认证公平自主决策算法，其中包含一个计算决策模块。决策策略和伪对抗性，向决策模块提供有关可能违反公平性的审计反馈，并提供公平性认证，但 FairGame 框架在概念上类似于强化学习中著名的演员批评家方法；与参与者-批评家方法相比，它强制审计员只能查询策略，相反，决策模块只能查询审计员（提供有关决策的反馈）。不同的公平性和有效性概念可以建模为不同的模型。该项目将研究该框架中的基本问题，包括（a）在黑盒环境中（概率上）证明公平性的可能性，（b）实用性。算法审计，(c) 确保在黑盒审计师的情况下做出公平决策的迭代方法，包括政策梯度方法和贝叶斯优化，以及 (d) 适当的公平性和有效性标准，以及 (e) 这些标准是否可以满足不同的要求监管模型，例如“关于逻辑的有意义的信息”的要求或法律强加的非歧视要求。 这项工作将通过开发公平算法为无家可归家庭提供服务的实际政策挑战来指导，并提供该领域的反馈。给主要利益相关者。这个奖项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，NSF 的法定使命被认为值得支持。

项目成果

Just Resource Allocation? How Algorithmic Predictions and Human Notions of Justice Interact

只是资源分配？

• 发表时间: 2022-01
• 期刊: Proceedings of the ACM Conference on Economics and Computation
• 作者: Kube, Amanda;Das, Sanmay;Fowler, Patrick J.;and Vorobeychik, Yevgeniy
• 通讯作者: and Vorobeychik, Yevgeniy

Trade-offs between Group Fairness Metrics in Societal Resource Allocation

社会资源配置中群体公平指标之间的权衡

• DOI: 10.1145/3531146.3533171
• 发表时间: 2022-01
• 期刊: and Transparency
• 作者: Mashiat, Tasfia;Gitiaux, Xavier;Rangwala, Huzefa;Fowler, Patrick J.;and Das, Sanmay
• 通讯作者: and Das, Sanmay

Probabilistic Generating Circuits

概率发生电路

• 发表时间: 2021-01
• 期刊: Proceedings of the 38th International Conference on Machine Learning
• 作者: Zhang, Honghua;Juba, Brendan;Van Den Broeck, Guy
• 通讯作者: Van Den Broeck, Guy

Race-Aware Algorithms: Fairness, Nondiscrimination and Affirmative Action

种族感知算法：公平、非歧视和平权行动

• 发表时间: 2022-01
• 期刊: California law review
• 影响因子: 2.4
• 作者: Kim; Pauline T
• 通讯作者: Pauline T

A Scalable Shannon Entropy Estimator

可扩展的香农熵估计器

• DOI: 10.1007/978-3-031-13185-1_18
• 发表时间: 2022-01
• 期刊: Lecture notes in computer science
• 作者: Golia, P.;Juba, B.;Meel, K.S.
• 通讯作者: Meel, K.S.