CAREER: Information-Theoretic Measures for Fairness and Explainability in High-Stakes Applications

职业：高风险应用中公平性和可解释性的信息论测量

• 批准号: 2340006
• 负责人: Sanghamitra Dutta
• 金额: $ 66.56万
• 依托单位: University of Maryland, College Park
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2024
• 资助国家: 美国
• 起止时间: 2024-01-15 至 2028-12-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2340006&HistoricalAwards=false
• 关键词: CAREER; Information; Theoretic; Measures; Fairness

Machine learning is becoming increasingly prevalent in various aspects of our lives, including several high-stakes applications, such as finance, education, and employment. These machine learning models have shown remarkable success at learning patterns present in the historical data. However, indiscriminate learning of all patterns can sometimes lead to unintended consequences, such as perpetuating disparities based on gender, race, and other protected attributes, that can adversely affect certain groups of people. This project seeks to advance the foundations of ethical and socially-responsible machine learning by empowering users to systematically identify, explain, and mitigate the sources of disparity. Rethinking the traditional paradigm of separately addressing fairness and explainability, this research project will jointly examine fairness and explainability through a unified information-theoretic lens. Furthermore, through extensive outreach and student engagements on the social impacts of machine learning, this project aims to instill interest in mathematically-principled approaches and STEM education among undergraduate and high-school students, particularly underrepresented minority students, to spearhead the next generation of socially-responsible technology.The research project will provide a novel information-theoretic view of responsible machine learning, by leveraging a body of work in information theory called Partial Information Decomposition (PID). PID is closely tethered to the principles of Blackwell sufficiency in statistical decision theory and provides a formal way of quantifying when a random variable is “more informative” than another with respect to a target variable. Combined with estimation and optimization techniques, this project will enable us to disentangle the joint information content that several random variables share about another target variable, e.g., protected attributes such as gender, race, age, nationality, etc. Four research thrusts will be investigated: (i) Providing an information-theoretic framework for explaining sources of disparity with respect to protected attributes (gender, race, etc.); (ii) Performing systematic feature selection and representation learning with disparity control; (iii) Investigating fundamental limits with a focus on distributed and federated settings; and (iv) Validating these findings on real-world datasets in finance and education. This research will lay the foundational guiding principles for engineers and policymakers so that AI can truly bring about social good.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.

机器学习在我们生活的各个方面都变得越来越普遍，包括金融，教育和就业等几种高风险应用。这些机器学习模型在历史数据中存在的学习模式方面取得了巨大的成功。但是，对所有模式的学习不加区分的学习有时会导致意想不到的后果，例如基于性别，种族和其他受保护属性的差异，可能会对某些人群产生不利影响。该项目旨在通过授权用户系统地识别，解释和减轻差异来源来推动道德和社会负责的机器学习的基础。该研究项目重新考虑了分别解决公平性和解释性的传统范式，将通过统一的信息理论镜头共同研究公平性和解释性。此外，通过大量的外展和学生参与机器学习的社会影响，该项目旨在灌输对数学上专业的方法的兴趣，并在本科和高中生和高中生中的学生中进行数学专业的方法和STEM教育，尤其是代表性不足的少数群体，尤其是代表性的少数群体，尤其是率领下一代社会责任心的信息，以提供一定的信息，以提供一定的信息，以提供一定的信息，以提供一定的信息信息，以提供一定的信息，以提供一定的信息，以提供一定的信息。分解（PID）。 PID与静态决策理论中Blackwell的原理紧密联系在一起，并提供了一种正式的量化方式，当随机变量比另一个相对于目标变量“更有用”时。结合估计和优化技术，该项目将使我们能够解散几个随机变量在另一个目标变量上共享的联合信息内容，例如，例如性别，种族，种族，年龄，国籍等受保护的属性。将研究四个研究推力：（i）提供一个与尊重尊重的范围的信息（i）提供了一个信息。 （ii）通过差异控制执行系统的特征选择和表示学习； （iii）调查基本限制，重点是分布式和联合设置； （iv）在金融和教育中对实际数据集验证这些发现。这项研究将为工程师和政策制定者提供基本指导原则，以便AI能够真正带来社会利益。该奖项反映了NSF的法定使命，并使用基金会的知识分子优点和更广泛的影响审查标准，通过评估来诚实地支持。