III:Small: Counterfactually Fair Machine Learning through Causal Modeling

III:Small：通过因果建模实现反事实公平机器学习

• 批准号: 1910284
• 负责人: Lu Zhang
• 金额: $ 48.48万
• 依托单位: University of Arkansas
• 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: 2021-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1910284&HistoricalAwards=false
• 关键词: III; Small; Counterfactually; Fair; Machine

Machine learning models play increasingly important roles in modern society. Various machine learning models have been built around the collection and use of historical data to automatically make important decisions like employment, loan approval, insurance, bail and criminal sentencing. It is imperative to ensure that the decisions made with the assistance of machine learning models are not subject to discrimination and social biases. To achieve this goal, fundamental questions including how to define fairness criteria and how to incorporate them into machine learning algorithms to build fair models must be answered. This project is to establish a unified framework for addressing these challenges. The framework is built upon causal inference theories to answer “what if” questions that are critical in judging discrimination and fairness. The successful outcome of this project will lead to advances in theoretical understanding of the application of causality to fairness and contribute to the limited base of knowledge in fair machine learning. The education program will involve, through courses and thesis projects, undergraduate and graduate students to enhance their knowledge and skills in solving problems in machine learning and artificial intelligence, and attract high school students especially those from underrepresented groups to pursue careers in STEM.This project proposes a unified framework for fair machine learning, which covers different types of fairness measures such as total discrimination, direct/indirect discrimination or counterfactual fairness, different levels of fairness such as group-level or individual-level, mixed data type such as categorical or numerical, different forms of equations in the causal model, and fairness in both the data and the model. Within the framework, the investigators will address the unidentifiability challenge in causal inference by digging into the deep-seated reasons of unidentifiability and deriving mathematical bounds for unidentifiable causal effects. With the developed techniques and tools, the investigators will develop quantitative measure for existing fairness notions as well as propose new fairness notions that are compatible with the framework. The investigators will incorporate proposed fairness measures into machine learning model construction. Finally, the investigators will make the proposed framework more generally applicable by handling the mixed-type variables via deep generative models and relaxing the Markovian assumption as semi-Markovian models.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.

机器学习模型在现代社会中发挥着越来越重要的作用。围绕历史数据的收集和使用，已经建立了各种机器学习模型，以自动做出重要决策，如就业，贷款审批，保险，保释和刑事判决。必须确保在机器学习模型的帮助下做出的决策不受歧视和社会偏见的影响。为了实现这一目标，必须回答一些基本问题，包括如何定义公平标准，以及如何将它们纳入机器学习算法以构建公平模型。该项目旨在建立一个统一的框架来应对这些挑战。该框架建立在因果推理理论的基础上，以回答在判断歧视和公平方面至关重要的“如果”问题。该项目的成功结果将导致对因果关系应用于公平的理论理解的进步，并有助于公平机器学习的有限知识基础。该教育计划将通过课程和论文项目，让本科生和研究生参与进来，提高他们解决机器学习和人工智能问题的知识和技能，并吸引高中生，特别是那些来自代表性不足的群体的学生从事STEM职业。该项目提出了一个统一的公平机器学习框架，其中涵盖了不同类型的公平措施，如完全歧视，直接/间接歧视或反事实公平，不同级别的公平，如群体级别或个人级别，混合数据类型，如分类或数字，因果模型中不同形式的方程，以及数据和模型的公平性。在这个框架内，研究人员将通过挖掘不可识别性的深层次原因和推导不可识别因果效应的数学界限来解决因果推理中的不可识别性挑战。随着开发的技术和工具，调查人员将开发现有的公平概念的量化措施，以及提出新的公平概念，是兼容的框架。研究人员将把拟议的公平性措施纳入机器学习模型的构建中。最后，研究人员将通过深度生成模型处理混合型变量，并将马尔可夫假设放宽为半马尔可夫模型，从而使拟议的框架更加普遍适用。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。

项目成果

On Root Cause Localization and Anomaly Mitigation through Causal Inference

• DOI: 10.1145/3583780.3614995
• 发表时间: 2022-12
• 期刊: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
• 作者: Xiao Han;Lu Zhang;Yongkai Wu;Shuhan Yuan

Achieving Long-Term Fairness in Sequential Decision Making

在顺序决策中实现长期公平

• DOI: 10.1609/aaai.v36i9.21188
• 发表时间: 2022
• 期刊: Proceedings of the AAAI Conference on Artificial Intelligence
• 作者: Hu, Yaowei;Zhang, Lu
• 通讯作者: Zhang, Lu

Achieving Counterfactual Fairness for Anomaly Detection

• DOI: 10.48550/arxiv.2303.02318
• 发表时间: 2023-03
• 期刊: Chinese Journal of Geophysics
• 作者: Xiao Han;Lu Zhang;Yongkai Wu;Shuhan Yuan

Robust Personalized Federated Learning under Demographic Fairness Heterogeneity

• DOI: 10.1109/bigdata55660.2022.10020554
• 发表时间: 2022-12
• 期刊: 2022 IEEE International Conference on Big Data (Big Data)
• 作者: Alycia N. Carey;Wei Du;Xintao Wu

Achieving Counterfactual Fairness for Causal Bandit

实现因果强盗的反事实公平

• DOI: 10.1609/aaai.v36i6.20653
• 发表时间: 2022
• 期刊: Proceedings of the AAAI Conference on Artificial Intelligence
• 作者: Huang, Wen;Zhang, Lu;Wu, Xintao
• 通讯作者: Wu, Xintao