FAI: Fairness in Machine Learning with Human in the Loop

FAI：机器学习中人的参与的公平性

• 批准号: 2040800
• 负责人: Yang Liu
• 金额: $ 62.5万
• 依托单位: University of California-Santa Cruz
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-02-01 至 2025-01-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2040800&HistoricalAwards=false
• 关键词: FAI; Fairness; Machine; Learning; Human

Despite early successes and significant potential, algorithmic decision-making systems often inherit and encode biases that exist in the training data and/or the training process. It is thus important to understand the consequences of deploying and using machine learning models and provide algorithmic treatments to ensure that such techniques will ultimately serve the social good. While recent works have looked into the fairness issues in AI concerning the “short-term” measures, the long-term consequences and impacts of automated decision making remain unclear. The understanding of the long-term impact of a fair decision provides guidelines to policy-makers when deploying an algorithmic model in a dynamic environment and is critical to its trustworthiness and adoption. It will also drive the design of algorithms with an eye toward the welfare of both the makers and the users of these algorithms, with an ultimate goal of achieving more equitable outcomes. This project aims to understand the long-term impact of fair decisions made by automated machine learning algorithms via establishing an analytical, algorithmic, and experimental framework that captures the sequential learning and decision process, the actions and dynamics of the underlying user population, and its welfare. This knowledge will help design the right fairness criteria and intervention mechanisms throughout the life cycle of the decision-action loop to ensure long-term equitable outcomes. Central to this project’s intellectual inquiry is the focus on human in the loop, i.e., an AI-human feedback loop with automated decision-making that involves human participation. Our focus on the long-term impacts of fair algorithmic decision-making while explicitly modeling and incorporating human agents in the loop provides a theoretically rigorous framework to understand how an algorithmic decision-maker fares in the foreseeable future.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.

尽管早期的成功和巨大的潜力，算法决策系统往往继承和编码存在于训练数据和/或训练过程中的偏见。 因此，重要的是要了解部署和使用机器学习模型的后果，并提供算法处理，以确保这些技术最终将服务于社会公益。虽然最近的工作已经研究了人工智能中关于“短期”措施的公平性问题，但自动决策的长期后果和影响仍然不清楚。对公平决策的长期影响的理解为政策制定者在动态环境中部署算法模型提供了指导，并且对其可信度和采用至关重要。它还将推动算法的设计，着眼于这些算法的制造者和用户的福利，最终目标是实现更公平的结果。 该项目旨在通过建立一个分析，算法和实验框架来理解自动机器学习算法做出的公平决策的长期影响，该框架捕获顺序学习和决策过程，底层用户群体的行为和动态及其福利。这一知识将有助于在整个决策-行动循环的生命周期中设计正确的公平标准和干预机制，以确保长期公平的结果。该项目的智力调查的核心是关注循环中的人，即，一个人工智能-人类反馈回路，具有涉及人类参与的自动决策。我们专注于公平算法决策的长期影响，同时明确建模并将人类代理纳入循环，这为理解算法决策者在可预见的未来的表现提供了一个理论上严格的框架。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知识价值和更广泛的影响审查标准进行评估来支持。

项目成果

Incentive Mechanisms for Strategic Classification and Regression Problems

战略分类与回归问题的激励机制

• DOI: 10.1145/3490486.3538300
• 发表时间: 2022
• 期刊: ACM Conference on Economics and Computation (EC
• 作者: Jin, Kun;Zhang, Xueru;Khalili, Mohammad Mahdi;Naghizadeh, Parinaz;Liu, Mingyan
• 通讯作者: Liu, Mingyan

Adaptive Data Debiasing through Bounded Exploration

通过有限探索进行自适应数据去偏

• 发表时间: 2022
• 期刊: Advances in neural information processing systems
• 作者: Yang, Yifan;Liu, Yang;Naghizadeh, Parinaz
• 通讯作者: Naghizadeh, Parinaz

Unintended Selection: Persistent Qualification Rate Disparities and Interventions

意外选择：持续存在的合格率差异和干预措施

• 发表时间: 2021
• 期刊: 35th Conference on Neural Information Processing Systems (NeurIPS 2021
• 作者: Raab, Reilly;Liu, Yang
• 通讯作者: Liu, Yang

Adaptive Adversarial Training Does Not Increase Recourse Costs

自适应对抗训练不会增加资源成本

• DOI: 10.1145/3600211.3604704
• 发表时间: 2023
• 期刊: ACM
• 作者: Hardy, Ian;Yetukuri, Jayanth;Liu, Yang
• 通讯作者: Liu, Yang

Understanding Instance-Level Label Noise: Disparate Impacts and Treatments

• 发表时间: 2021-02
• 作者: Yang Liu