CIF: Small: Foundations and Applications of Blind Subgroup Robustness

CIF：小：盲子群鲁棒性的基础和应用

• 批准号: 2120018
• 负责人: Guillermo Sapiro
• 金额: $ 45.11万
• 依托单位: Duke University
• 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=2120018&HistoricalAwards=false
• 关键词: CIF; Small; Foundations; Applications; Blind

Machine-learning algorithms may present discriminatory behavior across certain subgroups, meaning that segments of the overall population are measurably under-served by the model, rendering the decisions unfair. The most common approaches to address this challenge consider that the algorithm has access to a set of predefined protected subgroups during training, and the goal is to learn a model that satisfies a certain notion of fairness/robustness across these subgroups. Perfect fairness can, in general, only be achieved by degrading the performance of the benefited subgroups without necessarily improving the disadvantaged and protected ones. This conflicts with ethical and legal notions of no-harm fairness, which are appropriate where quality of service is paramount, for example in health. To address this, this work considers notions of fairness and subgroup robustness that guarantee no unnecessary harm is done to any subgroup. The project goes beyond this since it considers the case where the subgroups or demographics are not known a priori and might even change with time and algorithm deployment. The project brings these concepts of blind and no-harm subgroup robustness and fairness to the area of backwards compatibility, where the goal is to guarantee that new machine-learning algorithms are compatible with previous ones; and to the area of federated learning, where multiple sites share data for the sake of mutual benefit. Lastly, potential connections of the proposed blind and no unnecessary-harm subgroup robustness with causal inference are investigated. The project first formally studies blind and no-unnecessary-harm (Pareto optimal) subgroup robustness, where the machine-learning algorithm needs to be robust to all possible subgroups of the data (given a minimal subgroup size), without necessarily knowing in advance the subgroups' defining characteristics. This is formally studied, including the tradeoffs and costs of protecting unknown subgroups and the corresponding optimization algorithm; concepts of data and optimization uncertainty are also included to model potential sacrifices a subgroup can make in benefit of others. Such formal study of blind subgroup robustness is an emerging field in the machine-learning community, and this project provides a fundamental and unifying view of it, combining theory with practice and critical information for policy makers. The project then extends the work to the area of backwards compatibility, with the goal to make all potential subgroups equally backwards compatible; and to federated learning, where the subgroup fairness and robustness is considered both across the silos/participants and inside each silo itself. Finally, thanks to the close mathematical connection between invariant features and causality, the project further considers this proposed unifying framework of blind subgroup robustness to study connections between the automatically discovered critical subgroups, their features, and causality. Health applications provide a unique testbed for the frameworks developed here.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.

机器学习算法可能会在某些亚组中呈现歧视性行为，这意味着该模型的整体人群的段性能不足，从而使决策不公平。应对这一挑战的最常见方法认为，该算法在培训过程中可以访问一组预定义的受保护子组，而目标是学习一个满足某些子组公平/鲁棒性概念的模型。通常，只有通过降低受益亚组的性能而不必改善弱势群体和受保护的亚组的表现，才能实现完美的公平。这与无害公平的道德和法律概念相抵触，这在服务质量至关重要的情况下是适当的，例如健康。为了解决这个问题，这项工作考虑了公平性和亚组鲁棒性的概念，这些概念保证对任何子组都不会造成不必要的伤害。该项目超出了这一点，因为它考虑了不知道该子组或人口统计学的情况，甚至可能随时间和算法部署而改变。该项目将这些盲人和无障碍子组鲁棒性和公平性的概念带到了向后兼容的领域，目的是确保新的机器学习算法与以前的算法兼容；以及联邦学习的领域，为了相互利益，多个站点共享数据。最后，研究了所提出的盲人的潜在联系，并且没有研究因果推断的不必要的损伤亚组鲁棒性。该项目首先正式研究了盲目的和无需障碍（帕累托最佳）亚组鲁棒性，其中机器学习算法需要对数据的所有可能子组都具有鲁棒性（给定最小的亚组大小），而不必事先知道子组的定义特征。对此进行了正式研究，包括保护未知子组的权衡和成本以及相应的优化算法；还包括数据和优化不确定性的概念，以模拟亚组可以使他人受益的潜在牺牲。这种对盲人组鲁棒性的正式研究是机器学习社区中的一个新兴领域，该项目为其提供了基本和统一的观点，将理论与实践和政策制定者的关键信息相结合。然后，该项目将工作扩展到向后兼容的区域，其目标是使所有潜在的子组平均向后兼容；以及联邦学习，在孤岛/参与者中以及每个孤岛本身内部都认为亚组公平和鲁棒性。最后，由于不变特征与因果关系之间的密切数学联系，该项目进一步考虑了这种提出的盲目亚组鲁棒性统一框架，以研究自动发现的关键亚组，其特征和因果关系之间的联系。健康应用程序为此处开发的框架提供了独特的测试床。该奖项反映了NSF的法定任务，并被认为是值得通过基金会的知识分子和更广泛影响的评论标准来评估值得支持的。

项目成果

Minimax Pareto Fairness: A Multi Objective Perspective

• 发表时间: 2020-07
• 期刊: Proceedings of machine learning research
• 作者: Natalia Martínez;Martín Bertrán;G. Sapiro

Using text to teach image retrieval

使用文本教授图像检索

• DOI: 10.1109/cvprw53098.2021.00180
• 发表时间: 2021
• 期刊: CVPR 2021 Workshop
• 作者: H. Dong, Z. Wang

Federated fairness without access to demographics

无法获取人口统计信息的联邦公平性

• 发表时间: 2023
• 期刊: NeurIPS 2022 Workshop on Federated Learning
• 作者: A. Papadaki, N. Martinez

Minimax Demographic Group Fairness in Federated Learning

• DOI: 10.1145/3531146.3533081
• 发表时间: 2022-01
• 期刊: Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency
• 作者: Afroditi Papadaki;Natalia Martínez;Martín Bertrán;G. Sapiro;Miguel R. D. Rodrigues

Robust Hybrid Learning With Expert Augmentation

• 发表时间: 2022-02
• 期刊: Trans. Mach. Learn. Res.
• 作者: Antoine Wehenkel;Jens Behrmann;Hsiang Hsu;G. Sapiro;Gilles Louppe and;J. Jacobsen