Growing use of machine learning in policy and social impact settings have raised concerns for fairness implications, especially for racial minorities. These concerns have generated considerable interest among machine learning and artificial intelligence researchers, who have developed new methods and established theoretical bounds for improving fairness, focusing on the source data, regularization and model training, or post-hoc adjustments to model scores. However, little work has studied the practical trade-offs between fairness and accuracy in real-world settings to understand how these bounds and methods translate into policy choices and impact on society. Our empirical study fills this gap by investigating the impact of mitigating disparities on accuracy, focusing on the common context of using machine learning to inform benefit allocation in resource-constrained programs across education, mental health, criminal justice, and housing safety. Here we describe applied work in which we find fairness-accuracy trade-offs to be negligible in practice. In each setting studied, explicitly focusing on achieving equity and using our proposed post-hoc disparity mitigation methods, fairness was substantially improved without sacrificing accuracy. This observation was robust across policy contexts studied, scale of resources available for intervention, time, and relative size of the protected groups. These empirical results challenge a commonly held assumption that reducing disparities either requires accepting an appreciable drop in accuracy or the development of novel, complex methods, making reducing disparities in these applications more practical.
Predictive models for identifying at-risk students early can help teaching staff direct resources to better support them, but there is a growing concern about the fairness of algorithmic systems in education. Predictive models may inadvertently introduce bias in who receives support and thereby exacerbate existing inequities. We examine this issue by building a predictive model of student success based on university administrative records. We find that the model exhibits gender and racial bias in two out of three fairness measures considered. We then apply post-hoc adjustments to improve model…
Carnegie Mellon University（卡内基梅隆大学）；JP Morgan（摩根大通）；JP Morgan AI Research（摩根大通人工智能研究院）；Determined AI
Group fairness, a class of fairness notions that measure how different groups of individuals are treated differently according to their protected attributes, has been shown to conflict with one another, often with a necessary cost in loss of model's predictive performance. We propose a general diagnostic that enables systematic characterization of these trade-offs in group fairness. We observe that the majority of group fairness notions can be expressed via the fairness-confusion tensor, which is the confusion matrix split according to the protected attribute values. We frame several optimizat…
Trade-offs Between Individual and Group Fairness in Machine Learning: A Comprehensive Review
Departamento de Estadística, Universidad Carlos III de Madrid（统计系，卡洛斯三世大学）；uc3m-Santander Big Data Institute (IBiDat), Universidad Carlos III de Madrid（圣安德烈斯-卡洛斯三世大学大数据研究所）；Department of Statistics and O.R., Universidad Nacional de Educación a Distancia (UNED), Madrid, Spain（统计与运筹学系，国家远程教育大学）
To avoid discriminatory uses of their data, organizations can learn to map them into a representation that filters out information related to sensitive attributes. However, all existing methods in fair representation learning generate a fairness-information trade-off. To achieve different points on the fairness-information plane, one must train different models. In this paper, we first demonstrate that fairness-information trade-offs are fully characterized by rate-distortion trade-offs. Then, we use this key result and propose SoFaiR, a single shot fair representation learning method that gen…
As multi-task models gain popularity in a wider range of machine learning applications, it is becoming increasingly important for practitioners to understand the fairness implications associated with those models. Most existing fairness literature focuses on learning a single task more fairly, while how ML fairness interacts with multiple tasks in the joint learning setting is largely under-explored. In this paper, we are concerned with how group fairness (e.g., equal opportunity, equalized odds) as an ML fairness concept plays out in the multi-task scenario. In multi-task learning, several ta…
You Only Debias Once: Towards Flexible Accuracy-Fairness Trade-offs at Inference Time
Case Western Reserve University（凯斯西储大学）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；North Carolina State University（北卡罗来纳州立大学）；Texas A&M University（德克萨斯农工大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；Rice University（莱斯大学）
Lehigh University（理海大学）；University of Coimbra（科英布拉大学）
In the application of machine learning to real-life decision-making systems, e.g., credit scoring and criminal justice, the prediction outcomes might discriminate against people with sensitive attributes, leading to unfairness. The commonly used strategy in fair machine learning is to include fairness as a constraint or a penalization term in the minimization of the prediction loss, which ultimately limits the information given to decision-makers. In this paper, we introduce a new approach to handle fairness by formulating a stochastic multi-objective optimization problem for which the corresp…
University of Southern California（南加利福尼亚大学）；USC Information Sciences Institute（南加利福尼亚大学信息科学研究所）
Explicit and implicit bias clouds human judgement, leading to discriminatory treatment of minority groups. A fundamental goal of algorithmic fairness is to avoid the pitfalls in human judgement by learning policies that improve the overall outcomes while providing fair treatment to protected classes. In this paper, we propose a causal framework that learns optimal intervention policies from data subject to fairness constraints. We define two measures of treatment bias and infer best treatment assignment that minimizes the bias while optimizing overall outcome. We demonstrate that there is a di…
With the fast development of algorithmic governance, fairness has become a compulsory property for machine learning models to suppress unintentional discrimination. In this paper, we focus on the pre-processing aspect for achieving fairness, and propose a data reweighing approach that only adjusts the weight for samples in the training phase. Different from most previous reweighing methods which usually assign a uniform weight for each (sub)group, we granularly model the influence of each training sample with regard to fairness-related quantity and predictive utility, and compute individual we…
University of Toronto（多伦多大学）；Vector Institute（向量研究所）
Deploying machine learning (ML) models often requires both fairness and privacy guarantees. Both of these objectives present unique trade-offs with the utility (e.g., accuracy) of the model. However, the mutual interactions between fairness, privacy, and utility are less well-understood. As a result, often only one objective is optimized, while the others are tuned as hyper-parameters. Because they implicitly prioritize certain objectives, such designs bias the model in pernicious, undetectable ways. To address this, we adopt impartiality as a principle: design of ML pipelines should not favor…
Recent discussion in the public sphere about algorithmic classification has involved tension between competing notions of what it means for a probabilistic classification to be fair to different groups. We formalize three fairness conditions that lie at the heart of these debates, and we prove that except in highly constrained special cases, there is no method that can satisfy these three conditions simultaneously. Moreover, even satisfying all three conditions approximately requires that the data lie in an approximate version of one of the constrained special cases identified by our theorem. …
IBM Research – T. J. Watson Research Center（IBM研究院–托马斯·J·沃森研究中心）；DataArt（数据艺术公司）；IBM Research – Africa（IBM研究院–非洲分院）
To ensure trust in AI models, it is becoming increasingly apparent that evaluation of models must be extended beyond traditional performance metrics, like accuracy, to other dimensions, such as fairness, explainability, adversarial robustness, and distribution shift. We describe an empirical study to evaluate multiple model types on various metrics along these dimensions on several datasets. Our results show that no particular model type performs well on all dimensions, and demonstrate the kinds of trade-offs involved in selecting models evaluated along multiple dimensions.
Lehigh University（利哈伊大学）；University of Coimbra（科英布拉大学）
In machine learning (ML) applications, unfair predictions may discriminate against a minority group. Most existing approaches for fair machine learning (FML) treat fairness as a constraint or a penalization term in the optimization of a ML model, which does not lead to the discovery of the complete landscape of the trade-offs among learning accuracy and fairness metrics, and does not integrate fairness in a meaningful way. Recently, we have introduced a new paradigm for FML based on Stochastic Multi-Objective Optimization (SMOO), where accuracy and fairness metrics stand as conflicting objecti…
Criminal recidivism models are tools that have gained widespread adoption by parole boards across the United States to assist with parole decisions. These models take in large amounts of data about an individual and then predict whether an individual would commit a crime if released on parole. Although such models are not the only or primary factor in making the final parole decision, questions have been raised about their accuracy, fairness, and interpretability. In this paper, various machine learning-based criminal recidivism models are created based on a real-world parole decision dataset …
Learning Heterogeneous Performance-Fairness Trade-offs in Federated Learning
Department of Computer Science and Engineering and the Research Institute of Trustworthy Autonomous Systems at Southern University of Science and Technology（计算机科学与工程系和可信自主系统研究 institute at 南方科技大学）
As machine learning (ML) systems get adopted in more critical areas, it has become increasingly crucial to address the bias that could occur in these systems. Several fairness pre-processing algorithms are available to alleviate implicit biases during model training. These algorithms employ different concepts of fairness, often leading to conflicting strategies with consequential trade-offs between fairness and accuracy. In this work, we evaluate three popular fairness pre-processing algorithms and investigate the potential for combining all algorithms into a more robust pre-processing ensembl…
In many machine learning settings there is an inherent tension between fairness and accuracy desiderata. How should one proceed in light of such trade-offs? In this work we introduce and study $γ$-disqualification, a new framework for reasoning about fairness-accuracy tradeoffs w.r.t a benchmark class $H$ in the context of supervised learning. Our requirement stipulates that a classifier should be disqualified if it is possible to improve its fairness by switching to another classifier from $H$ without paying "too much" in accuracy. The notion of "too much" is quantified via a parameter $γ$ th…
The fairness of machine learning-based decisions has become an increasingly important focus in the design of supervised machine learning methods. Most fairness approaches optimize a specified trade-off between performance measure(s) (e.g., accuracy, log loss, or AUC) and fairness metric(s) (e.g., demographic parity, equalized odds). This begs the question: are the right performance-fairness trade-offs being specified? We instead re-cast fair machine learning as an imitation learning task by introducing superhuman fairness, which seeks to simultaneously outperform human decisions on multiple pr…
In dimensionality reduction problems, the adopted technique may produce disparities between the representation errors of different groups. For instance, in the projected space, a specific class can be better represented in comparison with another one. In some situations, this unfair result may introduce ethical concerns. Aiming at overcoming this inconvenience, a fairness measure can be considered when performing dimensionality reduction through Principal Component Analysis. However, a solution that increases fairness tends to increase the overall re-construction error. In this context, this p…
A Theoretical Approach to Characterize the Accuracy-Fairness Trade-off Pareto Frontier
Shanghai Jiao Tong University（上海交通大学）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）；University of Georgia（佐治亚大学）；New Jersey Institute of Technology（新泽西理工学院）
A distinction has been drawn in fair machine learning research between `group' and `individual' fairness measures. Many technical research papers assume that both are important, but conflicting, and propose ways to minimise the trade-offs between these measures. This paper argues that this apparent conflict is based on a misconception. It draws on theoretical discussions from within the fair machine learning research, and from political and legal philosophy, to argue that individual and group fairness are not fundamentally in conflict. First, it outlines accounts of egalitarian fairness which …
The use of machine learning to guide clinical decision making has the potential to worsen existing health disparities. Several recent works frame the problem as that of algorithmic fairness, a framework that has attracted considerable attention and criticism. However, the appropriateness of this framework is unclear due to both ethical as well as technical considerations, the latter of which include trade-offs between measures of fairness and model performance that are not well-understood for predictive models of clinical outcomes. To inform the ongoing debate, we conduct an empirical study to…
Considerable research effort has been guided towards algorithmic fairness but there is still no major breakthrough. In practice, an exhaustive search over all possible techniques and hyperparameters is needed to find optimal fairness-accuracy trade-offs. Hence, coupled with the lack of tools for ML practitioners, real-world adoption of bias reduction methods is still scarce. To address this, we present Fairband, a bandit-based fairness-aware hyperparameter optimization (HO) algorithm. Fairband is conceptually simple, resource-efficient, easy to implement, and agnostic to both the objective met…
