In an attempt to make algorithms fair, the machine learning literature has largely focused on equalizing decisions, outcomes, or error rates across race or gender groups. To illustrate, consider a hypothetical government rideshare program that provides transportation assistance to low-income people with upcoming court dates. Following this literature, one might allocate rides to those with the highest estimated treatment effect per dollar, while constraining spending to be equal across race groups. That approach, however, ignores the downstream consequences of such constraints, and, as a result, can induce unexpected harms. For instance, if one demographic group lives farther from court, enforcing equal spending would necessarily mean fewer total rides provided, and potentially more people penalized for missing court. Here we present an alternative framework for designing equitable algorithms that foregrounds the consequences of decisions. In our approach, one first elicits stakeholder preferences over the space of possible decisions and the resulting outcomes--such as preferences for balancing spending parity against court appearance rates. We then optimize over the space of decision policies, making trade-offs in a way that maximizes the elicited utility. To do so, we develop an algorithm for efficiently learning these optimal policies from data for a large family of expressive utility functions. In particular, we use a contextual bandit algorithm to explore the space of policies while solving a convex optimization problem at each step to estimate the best policy based on the available information. This consequentialist paradigm facilitates a more holistic approach to equitable decision-making.
Department of Information Systems（信息系统系）；The Hilltop Institute（山顶研究所）；University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）
Healthcare programs such as Medicaid provide crucial services to vulnerable populations, but due to limited resources, many of the individuals who need these services the most languish on waiting lists. Survival models, e.g. the Cox proportional hazards model, can potentially improve this situation by predicting individuals' levels of need, which can then be used to prioritize the waiting lists. Providing care to those in need can prevent institutionalization for those individuals, which both improves quality of life and reduces overall costs. While the benefits of such an approach are clear, …
Predictive algorithms are now used to help distribute a large share of our society's resources and sanctions, such as healthcare, loans, criminal detentions, and tax audits. Under the right circumstances, these algorithms can improve the efficiency and equity of decision-making. At the same time, there is a danger that the algorithms themselves could entrench and exacerbate disparities, particularly along racial, ethnic, and gender lines. To help ensure their fairness, many researchers suggest that algorithms be subject to at least one of three constraints: (1) no use of legally protected feat…
Harvard University（哈佛大学）；University of Maryland, College Park（马里兰大学帕克分校）
Clustering is a fundamental problem in unsupervised machine learning, and fair variants of it have recently received significant attention due to its societal implications. In this work we introduce a novel definition of individual fairness for clustering problems. Specifically, in our model, each point $j$ has a set of other points $\mathcal{S}_j$ that it perceives as similar to itself, and it feels that it is fairly treated if the quality of service it receives in the solution is $α$-close (in a multiplicative sense, for a given $α\geq 1$) to that of the points in $\mathcal{S}_j$. We begin o…
Equitable Survival Prediction: A Fairness-Aware Survival Modeling (FASM) Approach
Duke-NUS Medical School（杜克-新加坡国立大学医学院）；Duke University School of Medicine（杜克大学医学院）；Duke AI Health（杜克人工智能健康中心）；Mass General Brigham（麻省总医院布里格姆）；Harvard Medical School（哈佛医学院）；National University of Singapore（新加坡国立大学）
On Demographic Group Fairness Guarantees in Deep Learning
Harvard AI and Robotics Lab at Harvard University（哈佛大学人工智能与机器人实验室）；Embodied AI and Robotics (AIR) Lab at New York University（纽约大学具身人工智能与机器人实验室）；School of Computing and Informatics, University of Louisiana at Lafayette（路易斯安那州立大学拉法叶分校计算机与信息学院）
What does it mean for a clustering to be fair? One popular approach seeks to ensure that each cluster contains groups in (roughly) the same proportion in which they exist in the population. The normative principle at play is balance: any cluster might act as a representative of the data, and thus should reflect its diversity. But clustering also captures a different form of representativeness. A core principle in most clustering problems is that a cluster center should be representative of the cluster it represents, by being "close" to the points associated with it. This is so that we can effe…
Effective machine learning models can automatically learn useful information from a large quantity of data and provide decisions in a high accuracy. These models may, however, lead to unfair predictions in certain sense among the population groups of interest, where the grouping is based on such sensitive attributes as race and gender. Various fairness definitions, such as demographic parity and equalized odds, were proposed in prior art to ensure that decisions guided by the machine learning models are equitable. Unfortunately, the "fair" model trained with these fairness definitions is thres…
Double Fairness Policy Learning: Integrating Action Fairness and Outcome Fairness in Decision-making
Department of Statistics（统计系）；Florida State University（佛罗里达州立大学）；Department of Management Science（管理科学系）；University of Miami（迈阿密大学）；London School of Economics and Political Science（伦敦政治经济学院）；Department of Decision Sciences（决策科学系）；George Washington University（乔治华盛顿大学）
What is Fair? Defining Fairness in Machine Learning for Health
Department of Statistical Sciences, University of Toronto（统计科学系，多伦多大学）；Harvard T.H. Chan School of Public Health（哈佛T.H. Chan公共卫生学院）；York University（约克大学）；Verily Life Sciences（Verily生命科学公司）；Duke University（杜克大学）；University of Toronto（多伦多大学）
Rethinking Algorithmic Fairness for Human-AI Collaboration
Wharton AI & Analytics Initiative, Wharton School, University of Pennsylvania（沃顿商学院人工智能与分析倡议，沃顿商学院，宾夕法尼亚大学）；Department of Operations, Information, and Decisions, Wharton School, University of Pennsylvania（运营、信息与决策系，沃顿商学院，宾夕法尼亚大学）；Department of Computer and Information Science, University of Pennsylvania（计算机与信息科学系，宾夕法尼亚大学）
Physics-Guided Fair Graph Sampling for Water Temperature Prediction in River Networks
University of Pittsburgh（匹兹堡大学）；University of Maryland（马里兰大学）；U.S. Geological Survey（美国地质调查局）；University of Florida（佛罗里达大学）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
University of Southern California（南加州大学）；Hamad Bin Khalifa University（哈马德·本·哈利法大学）
Machine learning (ML) is playing an increasing role in decision-making tasks that directly affect individuals, e.g., loan approvals, or job applicant screening. Significant concerns arise that, without special provisions, individuals from under-privileged backgrounds may not get equitable access to services and opportunities. Existing research studies fairness with respect to protected attributes such as gender, race or income, but the impact of location data on fairness has been largely overlooked. With the widespread adoption of mobile apps, geospatial attributes are increasingly used in ML,…
Georgia Tech（佐治亚理工学院）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
We show that the popular k-means clustering algorithm (Lloyd's heuristic), used for a variety of scientific data, can result in outcomes that are unfavorable to subgroups of data (e.g., demographic groups). Such biased clusterings can have deleterious implications for human-centric applications such as resource allocation. We present a fair k-means objective and algorithm to choose cluster centers that provide equitable costs for different groups. The algorithm, Fair-Lloyd, is a modification of Lloyd's heuristic for k-means, inheriting its simplicity, efficiency, and stability. In comparison w…
Trilateral Research（三边研究公司）；Data Justice Lab, Cardiff University（卡迪夫大学数据正义实验室）；University of Granada（格拉纳达大学）
Fair machine learning works have been focusing on the development of equitable algorithms that address discrimination of certain groups. Yet, many of these fairness-aware approaches aim to obtain a unique solution to the problem, which leads to a poor understanding of the statistical limits of bias mitigation interventions. We present the first methodology that allows to explore those limits within a multi-objective framework that seeks to optimize any measure of accuracy and fairness and provides a Pareto front with the best feasible solutions. In this work, we focus our study on decision tre…
