The machine learning community has become increasingly concerned with the potential for bias and discrimination in predictive models. This has motivated a growing line of work on what it means for a classification procedure to be "fair." In this paper, we investigate the tension between minimizing error disparity across different population groups while maintaining calibrated probability estimates. We show that calibration is compatible only with a single error constraint (i.e. equal false-negatives rates across groups), and show that any algorithm that satisfies this relaxation is no better than randomizing a percentage of predictions for an existing classifier. These unsettling findings, which extend and generalize existing results, are empirically confirmed on several datasets.
Politecnico di Milano（米兰理工大学）；Zurich University of Applied Sciences（苏黎世应用科学大学）
In this paper, we provide a moral analysis of two criteria of statistical fairness debated in the machine learning literature: 1) calibration between groups and 2) equality of false positive and false negative rates between groups. In our paper, we focus on moral arguments in support of either measure. The conflict between group calibration vs. false positive and false negative rate equality is one of the core issues in the debate about group fairness definitions among practitioners. For any thorough moral analysis, the meaning of the term fairness has to be made explicit and defined properly.…
We clarify what fairness guarantees we can and cannot expect to follow from unconstrained machine learning. Specifically, we characterize when unconstrained learning on its own implies group calibration, that is, the outcome variable is conditionally independent of group membership given the score. We show that under reasonable conditions, the deviation from satisfying group calibration is upper bounded by the excess risk of the learned score relative to the Bayes optimal score function. A lower bound confirms the optimality of our upper bound. Moreover, we prove that as the excess risk of the…
Stanford Center for Biomedical Informatics Research（斯坦福生物医学信息学研究中心）；Stanford University（斯坦福大学）
A growing body of work uses the paradigm of algorithmic fairness to frame the development of techniques to anticipate and proactively mitigate the introduction or exacerbation of health inequities that may follow from the use of model-guided decision-making. We evaluate the interplay between measures of model performance, fairness, and the expected utility of decision-making to offer practical recommendations for the operationalization of algorithmic fairness principles for the development and evaluation of predictive models in healthcare. We conduct an empirical case-study via development of …
Decision makers increasingly rely on algorithmic risk scores to determine access to binary treatments including bail, loans, and medical interventions. In these settings, we reconcile two fairness criteria that were previously shown to be in conflict: calibration and error rate equality. In particular, we derive necessary and sufficient conditions for the existence of calibrated scores that yield classifications achieving equal error rates at any given group-blind threshold. We then present an algorithm that searches for the most accurate score subject to both calibration and minimal error rat…
University of Maryland（马里兰大学）；Wellesley College（韦尔斯利学院）；Carnegie Mellon University（卡内基梅隆大学）；Northwestern University（西北大学）
Clustering is a foundational problem in machine learning with numerous applications. As machine learning increases in ubiquity as a backend for automated systems, concerns about fairness arise. Much of the current literature on fairness deals with discrimination against protected classes in supervised learning (group fairness). We define a different notion of fair clustering wherein the probability that two points (or a community of points) become separated is bounded by an increasing function of their pairwise distance (or community diameter). We capture the situation where data points repres…
Recent research on algorithmic fairness has highlighted that the problem formulation phase of ML system development can be a key source of bias that has significant downstream impacts on ML system fairness outcomes. However, very little attention has been paid to methods for improving the fairness efficacy of this critical phase of ML system development. Current practice neither accounts for the dynamic complexity of high-stakes domains nor incorporates the perspectives of vulnerable stakeholders. In this paper we introduce community based system dynamics (CBSD) as an approach to enable the pa…
Columbia University（哥伦比亚大学）；Harvard University（哈佛大学）；Rutgers University（罗格斯大学）
Multi-calibration is a powerful and evolving concept originating in the field of algorithmic fairness. For a predictor $f$ that estimates the outcome $y$ given covariates $x$, and for a function class $\mathcal{C}$, multi-calibration requires that the predictor $f(x)$ and outcome $y$ are indistinguishable under the class of auditors in $\mathcal{C}$. Fairness is captured by incorporating demographic subgroups into the class of functions~$\mathcal{C}$. Recent work has shown that, by enriching the class $\mathcal{C}$ to incorporate appropriate propensity re-weighting functions, multi-calibration…
Recovering Fairness Directly from Modularity: a New Way for Fair Community Partitioning
School of Mathematics and Statistics（数学与统计学学院）；Xidian University（西安电子科技大学）；City Faculty of Data Science（数据科学城市学院）；University of Macau（澳门大学）；College of Mathematical Medicine（数学医学学院）；Zhejiang Normal University（浙江师范大学）
With the increasing pervasive use of machine learning in social and economic settings, there has been an interest in the notion of machine bias in the AI community. Models trained on historic data reflect biases that exist in society and propagated them to the future through their decisions. There are three prominent metrics of machine fairness used in the community, and it has been shown statistically that it is impossible to satisfy them all at the same time. This has led to an ambiguity with regards to the definition of fairness. In this report, a causal perspective to the impossibility the…
McGill University（麦吉尔大学）；Mila（米拉研究所）；Université de Montréal（蒙特利尔大学）
Despite being widely used, face recognition models suffer from bias: the probability of a false positive (incorrect face match) strongly depends on sensitive attributes such as the ethnicity of the face. As a result, these models can disproportionately and negatively impact minority groups, particularly when used by law enforcement. The majority of bias reduction methods have several drawbacks: they use an end-to-end retraining approach, may not be feasible due to privacy issues, and often reduce accuracy. An alternative approach is post-processing methods that build fairer decision classifier…
In this work, the problem of predicting dropout risk in undergraduate studies is addressed from a perspective of algorithmic fairness. We develop a machine learning method to predict the risks of university dropout and underperformance. The objective is to understand if such a system can identify students at risk while avoiding potential discriminatory biases. When modeling both risks, we obtain prediction models with an Area Under the ROC Curve (AUC) of 0.77-0.78 based on the data available at the enrollment time, before the first year of studies starts. This data includes the students' demog…
Beijing University of Posts and Telecommunications（北京邮电大学）；BioMap（百图生科）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）
Recent studies show that graph convolutional network (GCN) often performs worse for low-degree nodes, exhibiting the so-called structural unfairness for graphs with long-tailed degree distributions prevalent in the real world. Graph contrastive learning (GCL), which marries the power of GCN and contrastive learning, has emerged as a promising self-supervised approach for learning node representations. How does GCL behave in terms of structural fairness? Surprisingly, we find that representations obtained by GCL methods are already fairer to degree bias than those learned by GCN. We theoretical…
Texas A&M University（德克萨斯农工大学）；Rice University（莱斯大学）；University of Georgia（佐治亚大学）
Machine learning models are becoming pervasive in high-stakes applications. Despite their clear benefits in terms of performance, the models could show discrimination against minority groups and result in fairness issues in a decision-making process, leading to severe negative impacts on the individuals and the society. In recent years, various techniques have been developed to mitigate the unfairness for machine learning models. Among them, in-processing methods have drawn increasing attention from the community, where fairness is directly taken into consideration during model design to induc…
We mathematically compare four competing definitions of group-level nondiscrimination: demographic parity, equalized odds, predictive parity, and calibration. Using the theoretical framework of Friedler et al., we study the properties of each definition under various worldviews, which are assumptions about how, if at all, the observed data is biased. We argue that different worldviews call for different definitions of fairness, and we specify the worldviews that, when combined with the desire to avoid a criterion for discrimination that we call disparity amplification, motivate demographic par…
Past literature has been effective in demonstrating ideological gaps in machine learning (ML) fairness definitions when considering their use in complex socio-technical systems. However, we go further to demonstrate that these definitions often misunderstand the legal concepts from which they purport to be inspired, and consequently inappropriately co-opt legal language. In this paper, we demonstrate examples of this misalignment and discuss the differences in ML terminology and their legal counterparts, as well as what both the legal and ML fairness communities can learn from these tensions. …
Towards unraveling calibration biases in medical image analysis
Hospital Italiano de Buenos Aires（布宜诺斯艾利斯意大利医院）；Universidad Tecnológica Nacional（国立技术大学）；Research Institute for Signals, Systems and Computational Intelligence sinc(i) (FICH-UNL/CONICET)（信号、系统与计算智能研究所sinc(i)（FICH-UNL/阿根廷国家科学与技术研究理事会））
A variety of fairness constraints have been proposed in the literature to mitigate group-level statistical bias. Their impacts have been largely evaluated for different groups of populations corresponding to a set of sensitive attributes, such as race or gender. Nonetheless, the community has not observed sufficient explorations for how imposing fairness constraints fare at an instance level. Building on the concept of influence function, a measure that characterizes the impact of a training example on the target model and its predictive performance, this work studies the influence of training…
A Fairness Audit of the Duckworth-Lewis-Stern Method: Format-Specific and Gender-Differential Bias, with an Interpretable Calibration Layer for Cricket Target Revision
Intesa Sanpaolo（联合圣保罗银行）；Fujitsu Laboratories of Europe（富士通欧洲研究院）
Algorithmic bias mitigation has been one of the most difficult conundrums for the data science community and Machine Learning (ML) experts. Over several years, there have appeared enormous efforts in the field of fairness in ML. Despite the progress toward identifying biases and designing fair algorithms, translating them into the industry remains a major challenge. In this paper, we present the initial results of an industrial open innovation project in the banking sector: we propose a general roadmap for fairness in ML and the implementation of a toolkit called BeFair that helps to identify …
Society increasingly relies on machine learning models for automated decision making. Yet, efficiency gains from automation have come paired with concern for algorithmic discrimination that can systematize inequality. Recent work has proposed optimal post-processing methods that randomize classification decisions for a fraction of individuals, in order to achieve fairness measures related to parity in errors and calibration. These methods, however, have raised concern due to the information inefficiency, intra-group unfairness, and Pareto sub-optimality they entail. The present work proposes a…
Motivated by scenarios where data is used for diverse prediction tasks, we study whether fair representation can be used to guarantee fairness for unknown tasks and for multiple fairness notions simultaneously. We consider seven group fairness notions that cover the concepts of independence, separation, and calibration. Against the backdrop of the fairness impossibility results, we explore approximate fairness. We prove that, although fair representation might not guarantee fairness for all prediction tasks, it does guarantee fairness for an important subset of tasks -- the tasks for which the…
Technical University of Denmark（丹麦技术大学）；Pioneer Centre for AI（人工智能先锋中心）；University of Copenhagen（哥本哈根大学）；Rigshospitalet（哥本哈根大学国立医院）
Recent work on algorithmic fairness has largely focused on the fairness of discrete decisions, or classifications. While such decisions are often based on risk score models, the fairness of the risk models themselves has received considerably less attention. Risk models are of interest for a number of reasons, including the fact that they communicate uncertainty about the potential outcomes to users, thus representing a way to enable meaningful human oversight. Here, we address fairness desiderata for risk score models. We identify the provision of similar epistemic value to different groups a…
MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Cambridge（剑桥大学）；Microsoft Research（微软研究院）；University of Oxford（牛津大学）；The Alan Turing Institute（艾伦·图灵研究所）；University College London（伦敦大学学院）
Causal approaches to fairness have seen substantial recent interest, both from the machine learning community and from wider parties interested in ethical prediction algorithms. In no small part, this has been due to the fact that causal models allow one to simultaneously leverage data and expert knowledge to remove discriminatory effects from predictions. However, one of the primary assumptions in causal modeling is that you know the causal graph. This introduces a new opportunity for bias, caused by misspecifying the causal model. One common way for misspecification to occur is via unmeasure…
Polytechnic University of Bari（巴里理工大学）；University of Bari（巴里大学）
The increasing application of Artificial Intelligence and Machine Learning models poses potential risks of unfair behavior and, in light of recent regulations, has attracted the attention of the research community. Several researchers focused on seeking new fairness definitions or developing approaches to identify biased predictions. However, none try to exploit the counterfactual space to this aim. In that direction, the methodology proposed in this work aims to unveil unfair model behaviors using counterfactual reasoning in the case of fairness under unawareness setting. A counterfactual ver…
Experian DataLabs UK&I and EMEA（益博睿英国爱尔兰及欧洲、中东和非洲数据实验室）
Understanding and removing bias from the decisions made by machine learning models is essential to avoid discrimination against unprivileged groups. Despite recent progress in algorithmic fairness, there is still no clear answer as to which bias-mitigation approaches are most effective. Evaluation strategies are typically use-case specific, rely on data with unclear bias, and employ a fixed policy to convert model outputs to decision outcomes. To address these problems, we performed a systematic comparison of a number of popular fairness algorithms applicable to supervised classification. Our …
University of Maryland, College Park（马里兰大学帕克分校）；Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）
As machine learning algorithms have been widely deployed across applications, many concerns have been raised over the fairness of their predictions, especially in high stakes settings (such as facial recognition and medical imaging). To respond to these concerns, the community has proposed and formalized various notions of fairness as well as methods for rectifying unfair behavior. While fairness constraints have been studied extensively for classical models, the effectiveness of methods for imposing fairness on deep neural networks is unclear. In this paper, we observe that these large models…
Machine learning models deployed in real-world applications are often evaluated with precision-based metrics such as F1-score or AUC-PR (Area Under the Curve of Precision Recall). Heavily dependent on the class prior, such metrics make it difficult to interpret the variation of a model's performance over different subpopulations/subperiods in a dataset. In this paper, we propose a way to calibrate the metrics so that they can be made invariant to the prior. We conduct a large number of experiments on balanced and imbalanced data to assess the behavior of calibrated metrics and show that they i…
In many real life situations, including job and loan applications, gatekeepers must make justified and fair real-time decisions about a person's fitness for a particular opportunity. In this paper, we aim to accomplish approximate group fairness in an online stochastic decision-making process, where the fairness metric we consider is equalized odds. Our work follows from the classical learning-from-experts scheme, assuming a finite set of classifiers (human experts, rules, options, etc) that cannot be modified. We run separate instances of the algorithm for each label class as well as sensitiv…
Texas State University（得克萨斯州立大学）；Illinois Institute of Technology（伊利诺伊理工学院）
Algorithmic bias is of increasing concern, both to the research community, and society at large. Bias in AI is more abstract and unintuitive than traditional forms of discrimination and can be more difficult to detect and mitigate. A clear gap exists in the current literature on evaluating the relative bias in the performance of multi-class classifiers. In this work, we propose two simple yet effective metrics, Combined Error Variance (CEV) and Symmetric Distance Error (SDE), to quantitatively evaluate the class-wise bias of two models in comparison to one another. By evaluating the performanc…
Machine Learning community is recently exploring the implications of bias and fairness with respect to the AI applications. The definition of fairness for such applications varies based on their domain of application. The policies governing the use of such machine learning system in a given context are defined by the constitutional laws of nations and regulatory policies enforced by the organizations that are involved in the usage. Fairness related laws and policies are often spread across the large documents like constitution, agreements, and organizational regulations. These legal documents …
