FAI: Advancing Optimization for Threshold-Agnostic Fair AI Systems

FAI：推进与阈值无关的公平人工智能系统的优化

• 批准号: 2147253
• 负责人: Tianbao Yang
• 金额: $ 50万
• 依托单位: University of Iowa
• 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: 2022-08-01 至 2022-10-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2147253&HistoricalAwards=false
• 关键词: FAI; Advancing; Optimization; Threshold; Agnostic

Artificial intelligence (AI) and machine learning technologies are being used in high-stakes decision-making systems like lending decision, employment screening, and criminal justice sentencing. A new challenge arising with these AI systems is avoiding the unfairness they might introduce and that can lead to discriminatory decisions for protected classes. Most AI systems use some kinds of thresholds to make decisions. This project aims to improve fairness-aware AI technologies by formulating threshold-agnostic metrics for decision making. In particular, the research team will improve the training procedures of fairness-constrained AI models to make the model adaptive to different contexts, applicable to different applications, and subject to emerging fairness constraints. The success of this project will yield a transferable approach to improve fairness in various aspects of society by eliminating the disparate impacts and enhancing the fairness of AI systems in the hands of the decision makers. Together with AI practitioners, the researchers will integrate the techniques in this project into real-world systems such as education analytics. This project will also contribute to training future professionals in AI and machine learning and broaden this activity by including training high school students and under-represented undergraduates. This project focuses on advancing optimization for threshold-agnostic fair AI systems. The research activities include: (i) developing scalable stochastic optimization algorithms for optimizing a broad family of rank-based threshold-agnostic objectives; (ii) developing novel threshold-agnostic fairness measures including Receiver Operating Characteristic curve (ROC) fairness, Area under the ROC Curve (AUC) fairness, etc. and studying the relationship between them and the existing fairness measures; (iii) developing efficient stochastic methods for in-processing fairness-aware learning methods to directly optimize threshold-agnostic objectives subject to new threshold-agnostic fairness-ensuring constraints; and, (iv) investigating effective end-to-end deep learning framework that not only automatically learns the feature representations, but also satisfies the fairness constraints. The algorithms will be evaluated on multiple tasks, including image recognition, recommendation, spatial-temporal hazard prediction, and predicting students’ performance.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)和机器学习技术正被用于高风险的决策系统，如贷款决策、就业筛选和刑事司法判决。这些人工智能系统带来的一个新挑战是避免它们可能带来的不公平，这可能会导致对受保护阶层的歧视性决定。大多数人工智能系统使用某些类型的阈值来做出决定。该项目旨在通过制定与门槛无关的决策指标来改进公平感知人工智能技术。特别是，研究团队将完善公平约束AI模型的训练程序，使模型适应不同的上下文，适用于不同的应用，并受制于新出现的公平约束。该项目的成功将产生一种可转移的方法，通过消除不同的影响并提高人工智能系统在决策者手中的公平性，来改善社会各方面的公平性。研究人员将与人工智能从业者一起，将该项目中的技术整合到教育分析等现实世界的系统中。该项目还将有助于培训未来的人工智能和机器学习专业人员，并通过包括培训高中生和代表性不足的本科生来扩大这一活动。该项目致力于推进与门槛无关的公平人工智能系统的优化。研究工作包括：(I)开发可扩展的随机优化算法来优化一大类基于排名的门限不可知目标；(Ii)开发新的门限不可知公平性度量，包括接收者操作特征曲线(ROC)公平性、ROC曲线下面积(AUC)公平性等，并研究它们与现有公平性度量之间的关系；(Iii)开发高效的随机方法来处理公平性感知学习方法，以在新的门限不可知公平性保证约束下直接优化门限不可知目标；研究有效的端到端深度学习框架，该框架不仅能自动学习特征表示，而且能满足公平性约束。这些算法将在多个任务上进行评估，包括图像识别、推荐、时空风险预测和预测学生的表现。该奖项反映了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

Debiased Imitation Learning for Modulated Temporal Point Processes

调制时间点过程的去偏模仿学习

• 发表时间: 2023
• 期刊: Proceedings of the SIAM International Conference on Data Mining
• 作者: Li, Zhuoqun;Zhou, Zihan;Sun, Mingxuan;Xu, Hongteng
• 通讯作者: Xu, Hongteng

Sparse Transformer Hawkes Process for Long Event Sequences

长事件序列的稀疏变压器霍克斯过程

• 发表时间: 2023
• 期刊: Part V
• 作者: Li, Zhuoqun;Sun, Mingxuan.
• 通讯作者: Sun, Mingxuan.