CAREER: Towards Long-term Fairness in Sequential Decision Making

职业：在顺序决策中实现长期公平

• 批准号: 2142725
• 负责人: Lu Zhang
• 金额: $ 59.72万
• 依托单位: University of Arkansas
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-04-15 至 2027-03-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2142725&HistoricalAwards=false
• 关键词: CAREER; Towards; Long; term; Fairness

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2)Fair machine learning, a research topic that aims to reduce discrimination and bias in machine-automated decisions, is one of the keys for enabling broad societal acceptance of large-scale deployments of AI systems including automated decision-making systems. Currently the majority of studies in fair machine learning are based on static settings where the machine model makes the decision only once for each individual after its deployment. However, in practical situations, the machine learning model will usually be deployed to make sequential decisions over a period of time. In such sequential decision-making settings, ensuring fairness for each single step does not guarantee fairness in the long-term, presenting a challenging and urgent problem to the fair machine learning community about achieving long-term fairness. This project will make a transformative change to fair machine learning by greatly advancing the understanding of fundamental issues of fairness in dynamic settings, shedding light on the path to addressing conflicts between inconsistent fairness concepts, and contributing to the limited base of knowledge in long-term fair machine learning which is imperative for many real-world applications. The education program will involve undergraduates, graduates and high school students to enhance their knowledge and skills in solving problems in machine learning and artificial intelligence, and attract students especially those from underrepresented groups to pursue careers in STEM.This project will set up the foundation for long-term fair machine learning by leveraging Pearl's Structural Causal Model. The investigator will focus on the sequential decision-making setting where decisions made in the past may have an impact on future data. Soft intervention will be utilized to capture the causal effect of the deployment of decision models. The investigator will develop universal formulations for the long-term fairness based on the causal model so that it can be measured by causal inference techniques. Then, depending on whether the decision maker has access to adequate historical data, the investigator will study both offline and online learning settings via three progressive research tasks: (1) to study strategies and algorithms for achieving long-term fairness given sufficient historical training data; (2) to study how to not only capture the dynamics in the history but also predict the data in the future so that the decision model built would be fair in the predictable future; and (3) to move on to online learning where the decision maker has few or no training data but could update the decision model in an online manner and wants to achieve fairness eventually. Finally, two realistic extensions including unidentifiable situations and semi-Markovian models will be studied.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.

该奖项全部或部分由2021年美国救援计划法案（公法117-2）资助，公平机器学习是一个旨在减少机器自动化决策中的歧视和偏见的研究课题，是使社会广泛接受大规模部署人工智能系统（包括自动化决策系统）的关键之一。目前，大多数关于公平机器学习的研究都是基于静态设置的，在静态设置中，机器模型在部署后只为每个人做一次决策。然而，在实际情况中，机器学习模型通常会被部署为在一段时间内做出顺序决策。在这种顺序决策环境中，确保每一步的公平性并不能保证长期的公平性，这给公平机器学习社区带来了一个具有挑战性和紧迫性的问题，即如何实现长期的公平性。该项目将通过极大地推进对动态设置中公平性基本问题的理解，为解决不一致公平概念之间的冲突提供光明，并为长期公平机器学习中有限的知识基础做出贡献，这对许多现实世界的应用至关重要。该教育计划将涉及本科生、研究生和高中生，以提高他们解决机器学习和人工智能问题的知识和技能，并吸引学生，特别是来自代表性不足的群体的学生从事STEM职业。该项目将利用Pearl的结构因果模型为长期公平的机器学习奠定基础。研究者将重点关注顺序决策设置，其中过去做出的决策可能会对未来数据产生影响。软干预将被用来捕捉决策模型部署的因果关系。研究者将根据因果模型开发长期公平性的通用公式，以便可以通过因果推理技术进行测量。然后，根据决策者是否能够获得足够的历史数据，研究者将通过三个渐进的研究任务来研究离线和在线学习设置：（1）研究策略和算法，以实现长期的公平性，给出足够的历史训练数据;（2）研究如何既能捕捉到历史上的动态，又能预测未来的数据，使所建立的决策模型在可预测的未来具有公平性;以及（3）转移到在线学习，其中决策者具有很少或没有训练数据，但是可以以在线方式更新决策模型并且希望最终实现公平。最后，两个现实的扩展，包括无法识别的情况和半马尔可夫模型将被研究。这个奖项反映了NSF的法定使命，并已被认为是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的支持。

项目成果

Striking a Balance in Fairness for Dynamic Systems Through Reinforcement Learning

• DOI: 10.1109/bigdata59044.2023.10386299
• 发表时间: 2023-12
• 期刊: 2023 IEEE International Conference on Big Data (BigData)
• 作者: Yaowei Hu;Jacob Lear;Lu Zhang

Long-term Fair Decision Making Through Deep Generative Models

通过深度生成模型进行长期公平决策

• 发表时间: 2024
• 期刊: Proceedings of the AAAI Conference on Artificial Intelligence
• 作者: Hu, Yaowei;Wu, Yongkai Wu;Zhang, Lu
• 通讯作者: Zhang, Lu