CRII: CIF: Information Theoretic Measures for Fairness-aware Supervised Learning

CRII：CIF：公平意识监督学习的信息论措施

• 批准号: 2246058
• 负责人: Mohamed Nafea
• 金额: $ 17.49万
• 依托单位: University of Detroit Mercy
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-06-01 至 2025-05-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2246058&HistoricalAwards=false
• 关键词: CRII; CIF; Information; Theoretic; Measures

Despite the growing success of Machine Learning (ML) systems in accomplishing complex tasks, their increasing use in making or aiding consequential decisions that affect people’s lives (e.g., university admission, healthcare, predictive policing) raises concerns about potential discriminatory practices. Unfair outcomes in ML systems result from historical biases in the data used to train them. A learning algorithm designed merely to minimize prediction error may inherit or even exacerbate such biases; particularly when observed attributes of individuals, critical for generating accurate decisions, are biased by their group identities (e.g., race or gender) due to existing social and cultural inequalities. Understanding and measuring these biases-- at the data level-- is a challenging yet crucial problem, leading to constructive insights and methodologies for debiasing the data and adapting the learning system to minimize discrimination, as well as raising the need for policy changes and infrastructural development. This project aims to establish a comprehensive framework for precisely quantifying the marginal impact of individuals’ attributes on accuracy and unfairness of decisions, using tools from information and game theories and causal inference, along with legal and social science definitions of fairness. This multi-disciplinary effort will provide guidelines and design insights for practitioners in the field of fair data-driven automated systems and inform the public debate on social consequences of artificial intelligence.The majority of previous work formulates the algorithmic fairness problem from the viewpoint of the learning algorithm by enforcing a statistical or counterfactual fairness constraint on the learner’s outcome and designing a learner that meets it. As the considered fairness problem originates from biased data, merely adding constraints to the prediction task might not provide a holistic view of its fundamental limitations. This project looks at the fairness problem through different lens, where instead of asking “for a given learner, how can we achieve fairness”?, it asks “for a given dataset, what are the inherent tradeoffs in the data, and based on these, what is the best learner we can design”?. In supervised learning models, the challenge in the proposed problem lies in the complex structures of correlation/causation among individuals’ attributes (covariates), their group identities (protected features), the target variable (label), and the prediction outcome (decision). In analyzing the dataset, the marginal impacts of covariates on the accuracy and discrimination of decisions are quantified from the data, via carefully designed measures accounting for the complex correlation/causation structures among variables and the inherent tension between accuracy and fairness objectives. Subsequently, methods to exploit the quantified impacts in guiding downstream ML systems to improve their achievable accuracy-fairness tradeoff will be investigated. Importantly, the proposed framework provides explainable solutions, where the inclusion of certain attributes in the learning system is explained by their importance for accurate as well as fair decisions.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.

尽管机器学习 (ML) 系统在完成复杂任务方面取得了越来越大的成功，但它们越来越多地用于制定或帮助影响人们生活的重大决策（例如大学录取、医疗保健、预测性警务），这引起了人们对潜在的不公平结果的担忧。机器学习系统是由用于训练它们的数据中的历史偏差产生的，仅仅为了最小化预测误差而设计的学习算法可能会继承甚至加剧这种偏差；特别是当观察到的对生成准确决策至关重要的个体属性受到其偏差的影响时。由于现有的社会和文化不平等而导致的群体身份（例如种族或性别）在数据层面上理解和衡量这些偏见是一个具有挑战性但又至关重要的问题，从而产生消除数据偏见和调整数据的建设性见解和方法。该项目旨在建立一个全面的框架，利用信息和博弈的工具，精确量化个人属性对决策准确性和不公平性的边际影响。理论和因果推理，以及公平的法律和社会科学定义，这项多学科的努力将为公平数据驱动的自动化系统领域的从业者提供指导和设计见解，并为有关人工智能社会后果的公众辩论提供信息。之前的大多数工作都是从学习算法的角度来制定算法公平性问题，通过对学习器的结果施加统计或反事实的公平性约束，并设计一个满足该约束的学习器，因为所考虑的公平性问题源于有偏差的数据，只是添加了约束。预测任务可能无法提供对其基本局限性的整体看法。这从不同的角度来看待公平性问题，它不是问“对于给定的学习者，我们如何实现公平性”？而是问“对于给定的数据集，什么是公平性”？数据中固有的权衡，并基于这些，我们可以设计什么是最好的学习器？”在监督学习模型中，所提出问题的挑战在于个体属性（协变量）之间的相关性/因果关系的复杂结构。 ，他们的群体身份（受保护特征）、目​​标变量（标签）和预测结果（决策）在分析数据集时，通过考虑复杂相关性的精心设计的措施，从数据中量化协变量对决策准确性和辨别力的边际影响。随后，将研究利用量化影响来指导下游机器学习系统改善其可实现的准确性与公平性权衡的方法。重要的是，所提出的框架提供了可解释的解决方案。将某些属性纳入学习系统是因为它们对于准确和公平决策的重要性。该奖项反映了 NSF 的法定使命，并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，被认为值得支持。