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 rate disparity. Applied to the COMPAS criminal risk assessment tool, we show that our method can eliminate error disparities while maintaining calibration. In a separate application to credit lending, we compare our procedure to the omission of sensitive features and show that it raises both profit and the probability that creditworthy individuals receive loans.
Algorithmic fairness has been framed as a newly emerging technology that mitigates systemic discrimination in automated decision-making, providing opportunities to improve fairness in information systems (IS). However, based on a state-of-the-art literature review, we argue that fairness is an inherently social concept and that technologies for algorithmic fairness should therefore be approached through a sociotechnical lens. We advance the discourse on algorithmic fairness as a sociotechnical phenomenon. Our research objective is to embed AF in the sociotechnical view of IS. Specifically, we …
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）
University of Michigan（密歇根大学）；IBM Research（IBM研究院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
Many instances of algorithmic bias are caused by subpopulation shifts. For example, ML models often perform worse on demographic groups that are underrepresented in the training data. In this paper, we study whether enforcing algorithmic fairness during training improves the performance of the trained model in the \emph{target domain}. On one hand, we conceive scenarios in which enforcing fairness does not improve performance in the target domain. In fact, it may even harm performance. On the other hand, we derive necessary and sufficient conditions under which enforcing algorithmic fairness l…
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Cambridge（剑桥大学）；Saarland University（萨尔大学）；The Alan Turing Institute（艾伦·图灵研究所）
Algorithmic fairness is typically studied from the perspective of predictions. Instead, here we investigate fairness from the perspective of recourse actions suggested to individuals to remedy an unfavourable classification. We propose two new fairness criteria at the group and individual level, which -- unlike prior work on equalising the average group-wise distance from the decision boundary -- explicitly account for causal relationships between features, thereby capturing downstream effects of recourse actions performed in the physical world. We explore how our criteria relate to others, su…
An increasing number of decisions regarding the daily lives of human beings are being controlled by artificial intelligence (AI) algorithms in spheres ranging from healthcare, transportation, and education to college admissions, recruitment, provision of loans and many more realms. Since they now touch on many aspects of our lives, it is crucial to develop AI algorithms that are not only accurate but also objective and fair. Recent studies have shown that algorithmic decision-making may be inherently prone to unfairness, even when there is no intention for it. This paper presents an overview o…
ETH Zürich（苏黎世联邦理工学院）；University of Zürich（苏黎世大学）；MPI-SWS（马克斯·普朗克软件系统研究所）
We map the recently proposed notions of algorithmic fairness to economic models of Equality of opportunity (EOP)---an extensively studied ideal of fairness in political philosophy. We formally show that through our conceptual mapping, many existing definition of algorithmic fairness, such as predictive value parity and equality of odds, can be interpreted as special cases of EOP. In this respect, our work serves as a unifying moral framework for understanding existing notions of algorithmic fairness. Most importantly, this framework allows us to explicitly spell out the moral assumptions under…
University of Michigan（密歇根大学）；Princeton University（普林斯顿大学）；Claudius Legal Intelligence（克劳迪乌斯法律智能公司）
The need to address representation biases and sentencing disparities in legal case data has long been recognized. Here, we study the problem of identifying and measuring biases in large-scale legal case data from an algorithmic fairness perspective. Our approach utilizes two regression models: A baseline that represents the decisions of a "typical" judge as given by the data and a "fair" judge that applies one of three fairness concepts. Comparing the decisions of the "typical" judge and the "fair" judge allows for quantifying biases across demographic groups, as we demonstrate in four case st…
University of Melbourne（墨尔本大学）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
Algorithmic fairness seeks to identify and correct sources of bias in machine learning algorithms. Confoundingly, ensuring fairness often comes at the cost of accuracy. We provide formal tools in this work for reconciling this fundamental tension in algorithm fairness. Specifically, we put to use the concept of Pareto optimality from multi-objective optimization and seek the fairness-accuracy Pareto front of a neural network classifier. We demonstrate that many existing algorithmic fairness methods are performing the so-called linear scalarization scheme which has severe limitations in recover…
University of Michigan（密歇根大学）；ShanghaiTech University（上海科技大学）；IBM Research（IBM研究院）；MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室）
We consider the task of enforcing individual fairness in gradient boosting. Gradient boosting is a popular method for machine learning from tabular data, which arise often in applications where algorithmic fairness is a concern. At a high level, our approach is a functional gradient descent on a (distributionally) robust loss function that encodes our intuition of algorithmic fairness for the ML task at hand. Unlike prior approaches to individual fairness that only work with smooth ML models, our approach also works with non-smooth models such as decision trees. We show that our algorithm conv…
MPI-SWS（马克斯·普朗克软件系统研究所）；Saarland University（萨尔兰大学）；University of Maryland（马里兰大学）；Cambridge University（剑桥大学）；Alan Turing Institute（艾伦·图灵研究所）
As algorithms are increasingly used to make important decisions that affect human lives, ranging from social benefit assignment to predicting risk of criminal recidivism, concerns have been raised about the fairness of algorithmic decision making. Most prior works on algorithmic fairness normatively prescribe how fair decisions ought to be made. In contrast, here, we descriptively survey users for how they perceive and reason about fairness in algorithmic decision making. A key contribution of this work is the framework we propose to understand why people perceive certain features as fair or u…
Algorithmic fairness and privacy are essential pillars of trustworthy machine learning. Fair machine learning aims at minimizing discrimination against protected groups by, for example, imposing a constraint on models to equalize their behavior across different groups. This can subsequently change the influence of training data points on the fair model, in a disproportionate way. We study how this can change the information leakage of the model about its training data. We analyze the privacy risks of group fairness (e.g., equalized odds) through the lens of membership inference attacks: inferr…
Oregon Department of Human Services (ODHS)（俄勒冈州人类服务部（ODHS））；Office of Reporting, Research, Analytics, and Implementation (ORRAI)（报告、研究、分析和实施办公室（ORRAI））
The algorithmic fairness of predictive analytic tools in the public sector has increasingly become a topic of rigorous exploration. While instruments pertaining to criminal recidivism and academic admissions, for example, have garnered much attention, the predictive instruments of Child Welfare jurisdictions have received considerably less attention. This is in part because comparatively few such instruments exist and because even fewer have been scrutinized through the lens of algorithmic fairness. In this work, we seek to address both of these gaps. To this end, a novel classification algori…
Cohort Shapley value is a model-free method of variable importance grounded in game theory that does not use any unobserved and potentially impossible feature combinations. We use it to evaluate algorithmic fairness, using the well known COMPAS recidivism data as our example. This approach allows one to identify for each individual in a data set the extent to which they were adversely or beneficially affected by their value of a protected attribute such as their race. The method can do this even if race was not one of the original predictors and even if it does not have access to a proprietary…
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 …
University of Michigan（密歇根大学）；University of Konstanz（康斯坦茨大学）；IBM Research（IBM研究院）；Princeton University（普林斯顿大学）；Stanford University（斯坦福大学）
Many instances of algorithmic bias are caused by distributional shifts. For example, machine learning (ML) models often perform worse on demographic groups that are underrepresented in the training data. In this paper, we leverage this connection between algorithmic fairness and distribution shifts to show that algorithmic fairness interventions can help ML models overcome distribution shifts, and that domain adaptation methods (for overcoming distribution shifts) can mitigate algorithmic biases. In particular, we show that (i) enforcing suitable notions of individual fairness (IF) can improve…
Universitat Pomepu Fabra（庞培法布拉大学）；Università degli Studi di Cagliari（卡利亚里大学）
Research in adversarial machine learning has shown how the performance of machine learning models can be seriously compromised by injecting even a small fraction of poisoning points into the training data. While the effects on model accuracy of such poisoning attacks have been widely studied, their potential effects on other model performance metrics remain to be evaluated. In this work, we introduce an optimization framework for poisoning attacks against algorithmic fairness, and develop a gradient-based poisoning attack aimed at introducing classification disparities among different groups i…
University of Chicago（芝加哥大学）；IBM Research AI（IBM研究院人工智能部门）
The use of machine learning (ML) in high-stakes societal decisions has encouraged the consideration of fairness throughout the ML lifecycle. Although data integration is one of the primary steps to generate high quality training data, most of the fairness literature ignores this stage. In this work, we consider fairness in the integration component of data management, aiming to identify features that improve prediction without adding any bias to the dataset. We work under the causal interventional fairness paradigm. Without requiring the underlying structural causal model a priori, we propose …
Increasingly, discrimination by algorithms is perceived as a societal and legal problem. As a response, a number of criteria for implementing algorithmic fairness in machine learning have been developed in the literature. This paper proposes the Continuous Fairness Algorithm (CFA$θ$) which enables a continuous interpolation between different fairness definitions. More specifically, we make three main contributions to the existing literature. First, our approach allows the decision maker to continuously vary between specific concepts of individual and group fairness. As a consequence, the algor…
Department of Computer Science and Engineering, Texas A&M University（德克萨斯农工大学计算机科学与工程系）；Department of Industrial and Systems Engineering, Texas A&M University（德克萨斯农工大学工业与系统工程系）
Deep learning is increasingly being used in high-stake decision making applications that affect individual lives. However, deep learning models might exhibit algorithmic discrimination behaviors with respect to protected groups, potentially posing negative impacts on individuals and society. Therefore, fairness in deep learning has attracted tremendous attention recently. We provide a review covering recent progresses to tackle algorithmic fairness problems of deep learning from the computational perspective. Specifically, we show that interpretability can serve as a useful ingredient to diagn…
University of Bristol（布里斯托尔大学）；RMIT University（皇家墨尔本理工大学）
Today, artificial intelligence systems driven by machine learning algorithms can be in a position to take important, and sometimes legally binding, decisions about our everyday lives. In many cases, however, these systems and their actions are neither regulated nor certified. To help counter the potential harm that such algorithms can cause we developed an open source toolbox that can analyse selected fairness, accountability and transparency aspects of the machine learning process: data (and their features), models and predictions, allowing to automatically and objectively report them to rele…
The increasing impact of algorithmic decisions on people's lives compels us to scrutinize their fairness and, in particular, the disparate impacts that ostensibly-color-blind algorithms can have on different groups. Examples include credit decisioning, hiring, advertising, criminal justice, personalized medicine, and targeted policymaking, where in some cases legislative or regulatory frameworks for fairness exist and define specific protected classes. In this paper we study a fundamental challenge to assessing disparate impacts in practice: protected class membership is often not observed in …
National University of Singapore（新加坡国立大学）；Univ. Lille（里尔大学）；Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；Centrale Lille（里尔中央理工学院）
In recent years, machine learning (ML) algorithms have been deployed in safety-critical and high-stake decision-making, where the fairness of algorithms is of paramount importance. Fairness in ML centers on detecting bias towards certain demographic populations induced by an ML classifier and proposes algorithmic solutions to mitigate the bias with respect to different fairness definitions. To this end, several fairness verifiers have been proposed that compute the bias in the prediction of an ML classifier--essentially beyond a finite dataset--given the probability distribution of input featu…
Understanding challenges to the interpretation of disaggregated evaluations of algorithmic fairness
Google Research, Mountain View, CA, USA（谷歌研究, 山景城, 加州, 美国）；Google DeepMind, Mountain View, CA, USA（谷歌深Mind, 山景城, 加州, 美国）；New York University, New York, NY, USA（纽约大学, 纽约, 纽约, 美国）；Massachusetts Institute of Technology, Cambridge, MA, USA（麻省理工学院, 柏林, 马萨诸塞, 美国）；The Hopsital for Sick Children, Toronto, ON, Canada（儿童医院, 温哥华, 加拿大）；Stanford University, Stanford, CA, USA（斯坦福大学, 斯坦福, 加州, 美国）
Algorithmic fairness is a new interdisciplinary field of study focused on how to measure whether a process, or algorithm, may unintentionally produce unfair outcomes, as well as whether or how the potential unfairness of such processes can be mitigated. Statistical discrimination describes a set of informational issues that can induce rational (i.e., Bayesian) decision-making to lead to unfair outcomes even in the absence of discriminatory intent. In this article, we provide overviews of these two related literatures and draw connections between them. The comparison illustrates both the confli…
Algorithms are now regularly used to decide whether defendants awaiting trial are too dangerous to be released back into the community. In some cases, black defendants are substantially more likely than white defendants to be incorrectly classified as high risk. To mitigate such disparities, several techniques recently have been proposed to achieve algorithmic fairness. Here we reformulate algorithmic fairness as constrained optimization: the objective is to maximize public safety while satisfying formal fairness constraints designed to reduce racial disparities. We show that for several past …
AT&T Chief Data Office（AT&T首席数据办公室）；Trustworthy ML Initiative（可信机器学习倡议）
New technologies and the availability of geospatial data have drawn attention to spatio-temporal biases present in society. For example: the COVID-19 pandemic highlighted disparities in the availability of broadband service and its role in the digital divide; the environmental justice movement in the United States has raised awareness to health implications for minority populations stemming from historical redlining practices; and studies have found varying quality and coverage in the collection and sharing of open-source geospatial data. Despite the extensive literature on machine learning (M…
As more researchers have become aware of and passionate about algorithmic fairness, there has been an explosion in papers laying out new metrics, suggesting algorithms to address issues, and calling attention to issues in existing applications of machine learning. This research has greatly expanded our understanding of the concerns and challenges in deploying machine learning, but there has been much less work in seeing how the rubber meets the road. In this paper we provide a case-study on the application of fairness in machine learning research to a production classification system, and offe…
What does it mean for an algorithm to be fair? Different papers use different notions of algorithmic fairness, and although these appear internally consistent, they also seem mutually incompatible. We present a mathematical setting in which the distinctions in previous papers can be made formal. In addition to characterizing the spaces of inputs (the "observed" space) and outputs (the "decision" space), we introduce the notion of a construct space: a space that captures unobservable, but meaningful variables for the prediction. We show that in order to prove desirable properties of the entire …
Tsinghua University（清华大学）；Zhejiang University（浙江大学）；Squirrel AI Learning（松鼠AI智适应教育）
Nowadays fairness issues have raised great concerns in decision-making systems. Various fairness notions have been proposed to measure the degree to which an algorithm is unfair. In practice, there frequently exist a certain set of variables we term as fair variables, which are pre-decision covariates such as users' choices. The effects of fair variables are irrelevant in assessing the fairness of the decision support algorithm. We thus define conditional fairness as a more sound fairness metric by conditioning on the fairness variables. Given different prior knowledge of fair variables, we de…
Harvard University（哈佛大学）；Institute for Quantitative Social Science（定量社会科学研究所）；University of Massachusetts（马萨诸塞大学）
Using the concept of principal stratification from the causal inference literature, we introduce a new notion of fairness, called principal fairness, for human and algorithmic decision-making. The key idea is that one should not discriminate among individuals who would be similarly affected by the decision. Unlike the existing statistical definitions of fairness, principal fairness explicitly accounts for the fact that individuals can be impacted by the decision. Furthermore, we explain how principal fairness differs from the existing causality-based fairness criteria. In contrast to the count…
Efforts to promote equitable public policy with algorithms appear to be fundamentally constrained by the "impossibility of fairness" (an incompatibility between mathematical definitions of fairness). This technical limitation raises a central question about algorithmic fairness: How can computer scientists and policymakers support equitable policy reforms with algorithms? In this article, I argue that promoting justice with algorithms requires reforming the methodology of algorithmic fairness. First, I diagnose the problems of the current methodology for algorithmic fairness, which I call "for…
University Of Minnesota（明尼苏达大学）；Carnegie Mellon University（卡内基梅隆大学）；University of Pennsylvania（宾夕法尼亚大学）
We consider settings in which the right notion of fairness is not captured by simple mathematical definitions (such as equality of error rates across groups), but might be more complex and nuanced and thus require elicitation from individual or collective stakeholders. We introduce a framework in which pairs of individuals can be identified as requiring (approximately) equal treatment under a learned model, or requiring ordered treatment such as "applicant Alice should be at least as likely to receive a loan as applicant Bob". We provide a provably convergent and oracle efficient algorithm for…
Max Planck Institute for Software Systems (MPI-SWS)（马克斯·普朗克软件系统研究所 (MPI-SWS)）；University of Cambridge（剑桥大学）；Alan Turing Institute（艾伦·图灵研究所）；Leverhulme Centre for the Future of Intelligence（李弗休姆未来智能中心）
Consider a binary decision making process where a single machine learning classifier replaces a multitude of humans. We raise questions about the resulting loss of diversity in the decision making process. We study the potential benefits of using random classifier ensembles instead of a single classifier in the context of fairness-aware learning and demonstrate various attractive properties: (i) an ensemble of fair classifiers is guaranteed to be fair, for several different measures of fairness, (ii) an ensemble of unfair classifiers can still achieve fair outcomes, and (iii) an ensemble of cl…
Fairness is increasingly recognized as a critical component of machine learning systems. However, it is the underlying data on which these systems are trained that often reflects discrimination, suggesting a data management problem. In this paper, we first make a distinction between associational and causal definitions of fairness in the literature and argue that the concept of fairness requires causal reasoning. We then review existing works and identify future opportunities for applying data management techniques to causal algorithmic fairness.
Data-driven predictive models are increasingly used in education to support students, instructors, and administrators. However, there are concerns about the fairness of the predictions and uses of these algorithmic systems. In this introduction to algorithmic fairness in education, we draw parallels to prior literature on educational access, bias, and discrimination, and we examine core components of algorithmic systems (measurement, model learning, and action) to identify sources of bias and discrimination in the process of developing and deploying these systems. Statistical, similarity-based…
Conventional algorithmic fairness is West-centric, as seen in its sub-groups, values, and methods. In this paper, we de-center algorithmic fairness and analyse AI power in India. Based on 36 qualitative interviews and a discourse analysis of algorithmic deployments in India, we find that several assumptions of algorithmic fairness are challenged. We find that in India, data is not always reliable due to socio-economic factors, ML makers appear to follow double standards, and AI evokes unquestioning aspiration. We contend that localising model fairness alone can be window dressing in India, whe…
University of Oxford（牛津大学）；Universitat de València（瓦伦西亚大学）
Current adoption of machine learning in industrial, societal and economical activities has raised concerns about the fairness, equity and ethics of automated decisions. Predictive models are often developed using biased datasets and thus retain or even exacerbate biases in their decisions and recommendations. Removing the sensitive covariates, such as gender or race, is insufficient to remedy this issue since the biases may be retained due to other related covariates. We present a regularization approach to this problem that trades off predictive accuracy of the learned models (with respect to…
Conventional algorithmic fairness is Western in its sub-groups, values, and optimizations. In this paper, we ask how portable the assumptions of this largely Western take on algorithmic fairness are to a different geo-cultural context such as India. Based on 36 expert interviews with Indian scholars, and an analysis of emerging algorithmic deployments in India, we identify three clusters of challenges that engulf the large distance between machine learning models and oppressed communities in India. We argue that a mere translation of technical fairness work to Indian subgroups may serve only a…
Algorithmic Fairness in AI Surrogates for End-of-Life Decision-Making
The Department of Computing & Software Systems University of Washington Bothell Harborview Medical Center, UW Medicine（计算与软件系统系华盛顿大学Bothell分校哈佛湾医疗中心，华盛顿大学医学部）
针对临终决策 AI 替代者，本文将主要公平概念映射到现实临终场景并跨道德传统考察，提出公平应包含道德代表性及对患者价值观、关系与世界观的忠实。
Institute for Artificial Intelligence, Tsinghua University（清华大学人工智能研究院）；University of Florida（佛罗里达大学）；Weill Cornell Medicine（威尔康奈尔医学院）
Algorithmic fairness has aroused considerable interests in data mining and machine learning communities recently. So far the existing research has been mostly focusing on the development of quantitative metrics to measure algorithm disparities across different protected groups, and approaches for adjusting the algorithm output to reduce such disparities. In this paper, we propose to study the problem of identification of the source of model disparities. Unlike existing interpretation methods which typically learn feature importance, we consider the causal relationships among feature variables …
University of Tübingen（蒂宾根大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
Algorithmic recourse aims to disclose the inner workings of the black-box decision process in situations where decisions have significant consequences, by providing recommendations to empower beneficiaries to achieve a more favorable outcome. To ensure an effective remedy, suggested interventions must not only be low-cost but also robust and fair. This goal is accomplished by providing similar explanations to individuals who are alike. This study explores the concept of individual fairness and adversarial robustness in causal algorithmic recourse and addresses the challenge of achieving both. …
Pennsylvania State University（宾夕法尼亚州立大学）；Purdue University（普渡大学）
As virtually all aspects of our lives are increasingly impacted by algorithmic decision making systems, it is incumbent upon us as a society to ensure such systems do not become instruments of unfair discrimination on the basis of gender, race, ethnicity, religion, etc. We consider the problem of determining whether the decisions made by such systems are discriminatory, through the lens of causal models. We introduce two definitions of group fairness grounded in causality: fair on average causal effect (FACE), and fair on average causal effect on the treated (FACT). We use the Rubin-Neyman pot…
Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）；Max Planck Institute for Research on Collective Goods（马克斯·普朗克集体商品研究所）；KAIST（韩国科学技术院）；Institute for Basic Science（基础科学研究院）；University of Cambridge（剑桥大学）；Alan Turing Institute（艾伦·图灵研究所）
A growing number of oversight boards and regulatory bodies seek to monitor and govern algorithms that make decisions about people's lives. Prior work has explored how people believe algorithmic decisions should be made, but there is little understanding of how individual factors like sociodemographics or direct experience with a decision-making scenario may affect their ethical views. We take a step toward filling this gap by exploring how people's perceptions of one aspect of procedural algorithmic fairness (the fairness of using particular features in an algorithmic decision) relate to their…
