The Fairness, Accountability, and Transparency in Machine Learning (FAT-ML) literature proposes a varied set of group fairness metrics to measure discrimination against socio-demographic groups that are characterized by a protected feature, such as gender or race.Such a system can be deemed as either fair or unfair depending on the choice of the metric. Several metrics have been proposed, some of them incompatible with each other.We do so empirically, by observing that several of these metrics cluster together in two or three main clusters for the same groups and machine learning methods. In addition, we propose a robust way to visualize multidimensional fairness in two dimensions through a Principal Component Analysis (PCA) of the group fairness metrics. Experimental results on multiple datasets show that the PCA decomposition explains the variance between the metrics with one to three components.
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；University of Tübingen（蒂宾根大学）；Massachusetts Institute of Technology（麻省理工学院）
Deep metric learning (DML) enables learning with less supervision through its emphasis on the similarity structure of representations. There has been much work on improving generalization of DML in settings like zero-shot retrieval, but little is known about its implications for fairness. In this paper, we are the first to evaluate state-of-the-art DML methods trained on imbalanced data, and to show the negative impact these representations have on minority subgroup performance when used for downstream tasks. In this work, we first define fairness in DML through an analysis of three properties…
Machine learning systems are often deployed for making critical decisions like credit lending, hiring, etc. While making decisions, such systems often encode the user's demographic information (like gender, age) in their intermediate representations. This can lead to decisions that are biased towards specific demographics. Prior work has focused on debiasing intermediate representations to ensure fair decisions. However, these approaches fail to remain fair with changes in the task or demographic distribution. To ensure fairness in the wild, it is important for a system to adapt to such change…
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…
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 …
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）
Societies often rely on human experts to take a wide variety of decisions affecting their members, from jail-or-release decisions taken by judges and stop-and-frisk decisions taken by police officers to accept-or-reject decisions taken by academics. In this context, each decision is taken by an expert who is typically chosen uniformly at random from a pool of experts. However, these decisions may be imperfect due to limited experience, implicit biases, or faulty probabilistic reasoning. Can we improve the accuracy and fairness of the overall decision making process by optimizing the assignment…
Helmholtz AI（亥姆霍兹AI）；Ecole Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）；Swisscom（瑞士电信）
The goal of fairness in classification is to learn a classifier that does not discriminate against groups of individuals based on sensitive attributes, such as race and gender. One approach to designing fair algorithms is to use relaxations of fairness notions as regularization terms or in a constrained optimization problem. We observe that the hyperbolic tangent function can approximate the indicator function. We leverage this property to define a differentiable relaxation that approximates fairness notions provably better than existing relaxations. In addition, we propose a model-agnostic mu…
In recent years, machine learning techniques have been increasingly applied in sensitive decision making processes, raising fairness concerns. Past research has shown that machine learning may reproduce and even exacerbate human bias due to biased training data or flawed model assumptions, and thus may lead to discriminatory actions. To counteract such biased models, researchers have proposed multiple mathematical definitions of fairness according to which classifiers can be optimized. However, it has also been shown that the outcomes generated by some fairness notions may be unsatisfactory. I…
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…
University of Pennsylvania（宾夕法尼亚大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
It has recently been shown that if feedback effects of decisions are ignored, then imposing fairness constraints such as demographic parity or equality of opportunity can actually exacerbate unfairness. We propose to address this challenge by modeling feedback effects as Markov decision processes (MDPs). First, we propose analogs of fairness properties for the MDP setting. Second, we propose algorithms for learning fair decision-making policies for MDPs. Finally, we demonstrate the need to account for dynamical effects using simulations on a loan applicant MDP.
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…
Machine learning algorithms are now frequently used in sensitive contexts that substantially affect the course of human lives, such as credit lending or criminal justice. This is driven by the idea that `objective' machines base their decisions solely on facts and remain unaffected by human cognitive biases, discriminatory tendencies or emotions. Yet, there is overwhelming evidence showing that algorithms can inherit or even perpetuate human biases in their decision making when they are based on data that contains biased human decisions. This has led to a call for fairness-aware machine learni…
Scuola Normale Superiore（比萨高等师范学校）；University of Pisa, Department of Computer Science（比萨大学计算机科学系）
Resilience to class imbalance and confounding biases, together with the assurance of fairness guarantees are highly desirable properties of autonomous decision-making systems with real-life impact. Many different targeted solutions have been proposed to address separately these three problems, however a unifying perspective seems to be missing. With this work, we provide a general formalization, showing that they are different expressions of unbalance. Following this intuition, we formulate a unified loss correction to address issues related to Fairness, Biases and Imbalances (FBI-loss). The c…
University of Zurich（苏黎世大学）；Zurich University of Applied Sciences（苏黎世应用科学大学）
Ensuring fairness of prediction-based decision making is based on statistical group fairness criteria. Which one of these criteria is the morally most appropriate one depends on the context, and its choice requires an ethical analysis. In this paper, we present a step-by-step procedure integrating three elements: (a) a framework for the moral assessment of what fairness means in a given context, based on the recently proposed general principle of "Fair equality of chances" (FEC) (b) a mapping of the assessment's results to established statistical group fairness criteria, and (c) a method for i…
On Prediction-Modelers and Decision-Makers: Why Fairness Requires More Than a Fair Prediction Model
Ca’ Foscari University of Venice（威尼斯大学）；European Centre for Living Technology（欧洲生活技术中心）；University of Zurich（苏黎世大学）；Zurich University of Applied Sciences（苏黎世应用科技大学）
University of Michigan（密歇根大学）；Michigan Tech Research Institute（密歇根理工大学研究所）；University of Utah（犹他大学）
This work facilitates ensuring fairness of machine learning in the real world by decoupling fairness considerations in compound decisions. In particular, this work studies how fairness propagates through a compound decision-making processes, which we call a pipeline. Prior work in algorithmic fairness only focuses on fairness with respect to one decision. However, many decision-making processes require more than one decision. For instance, hiring is at least a two stage model: deciding who to interview from the applicant pool and then deciding who to hire from the interview pool. Perhaps surpr…
This paper proposes SCALES, a general framework that translates well-established fairness principles into a common representation based on the Constraint Markov Decision Process (CMDP). With the help of causal language, our framework can place constraints on both the procedure of decision making (procedural fairness) as well as the outcomes resulting from decisions (outcome fairness). Specifically, we show that well-known fairness principles can be encoded either as a utility component, a non-causal component, or a causal component in a SCALES-CMDP. We illustrate SCALES using a set of case stu…
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。
Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Schwartz Reisman Institute for Technology and Society（施瓦茨·赖斯曼技术与社会研究所）；University of Waterloo（滑铁卢大学）
Zurich University of Applied Sciences（苏黎世应用科学大学）；University of Zurich（苏黎世大学）
While the field of algorithmic fairness has brought forth many ways to measure and improve the fairness of machine learning models, these findings are still not widely used in practice. We suspect that one reason for this is that the field of algorithmic fairness came up with a lot of definitions of fairness, which are difficult to navigate. The goal of this paper is to provide data scientists with an accessible introduction to group fairness metrics and to give some insight into the philosophical reasoning for caring about these metrics. We will do this by considering in which sense socio-dem…
Dataset bias is one of the prevailing causes of unfairness in machine learning. Addressing fairness at the data collection and dataset preparation stages therefore becomes an essential part of training fairer algorithms. In particular, active learning (AL) algorithms show promise for the task by drawing importance to the most informative training samples. However, the effect and interaction between existing AL algorithms and algorithmic fairness remain under-explored. In this paper, we study whether models trained with uncertainty-based AL heuristics such as BALD are fairer in their decisions …
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…
Long-term fairness is an important factor of consideration in designing and deploying learning-based decision systems in high-stake decision-making contexts. Recent work has proposed the use of Markov Decision Processes (MDPs) to formulate decision-making with long-term fairness requirements in dynamically changing environments, and demonstrated major challenges in directly deploying heuristic and rule-based policies that worked well in static environments. We show that policy optimization methods from deep reinforcement learning can be used to find strictly better decision policies that can o…
University of Zurich（苏黎世大学）；Zurich University of Applied Sciences（苏黎世应用科学大学）
Binary decision making classifiers are not fair by default. Fairness requirements are an additional element to the decision making rationale, which is typically driven by maximizing some utility function. In that sense, algorithmic fairness can be formulated as a constrained optimization problem. This paper contributes to the discussion on how to implement fairness, focusing on the fairness concepts of positive predictive value (PPV) parity, false omission rate (FOR) parity, and sufficiency (which combines the former two). We show that group-specific threshold rules are optimal for PPV parity …
Data-driven decision making related to individuals has become increasingly pervasive, but the issue concerning the potential discrimination has been raised by recent studies. In response, researchers have made efforts to propose and implement fairness measures and algorithms, but those efforts have not been translated to the real-world practice of data-driven decision making. As such, there is still an urgent need to create a viable tool to facilitate fair decision making. We propose FairSight, a visual analytic system to address this need; it is designed to achieve different notions of fairne…
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）
University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；Leibniz University Hannover（汉诺威莱布尼茨大学）
Automated data-driven decision-making systems are ubiquitous across a wide spread of online as well as offline services. These systems, depend on sophisticated learning algorithms and available data, to optimize the service function for decision support assistance. However, there is a growing concern about the accountability and fairness of the employed models by the fact that often the available historic data is intrinsically discriminatory, i.e., the proportion of members sharing one or more sensitive attributes is higher than the proportion in the population as a whole when receiving positi…
Was it fair that Harry was hired but not Barry? Was it fair that Pam was fired instead of Sam? How can one ensure fairness when an intelligent algorithm takes these decisions instead of a human? How can one ensure that the decisions were taken based on merit and not on protected attributes like race or sex? These are the questions that must be answered now that many decisions in real life can be made through machine learning. However research in fairness of algorithms has focused on the counterfactual questions "what if?" or "why?", whereas in real life most subjective questions of consequence…
University of Michigan（密歇根大学）；Bilkent University（比尔肯特大学）
Machine Learning (ML) models trained on data from multiple demographic groups can inherit representation disparity (Hashimoto et al., 2018) that may exist in the data: the model may be less favorable to groups contributing less to the training process; this in turn can degrade population retention in these groups over time, and exacerbate representation disparity in the long run. In this study, we seek to understand the interplay between ML decisions and the underlying group representation, how they evolve in a sequential framework, and how the use of fairness criteria plays a role in this pro…
University of Oslo（奥斯陆大学）；Chalmers University（查尔姆斯理工大学）；UC Santa Cruz（加州大学圣克鲁兹分校）；Harvard University（哈佛大学）
We consider the problem of how decision making can be fair when the underlying probabilistic model of the world is not known with certainty. We argue that recent notions of fairness in machine learning need to explicitly incorporate parameter uncertainty, hence we introduce the notion of {\em Bayesian fairness} as a suitable candidate for fair decision rules. Using balance, a definition of fairness introduced by Kleinberg et al (2016), we show how a Bayesian perspective can lead to well-performing, fair decision rules even under high uncertainty.
North Carolina State University（北卡罗来纳州立大学）；Indian Institute of Management（印度管理学院）
Machine learning has become more important in real-life decision-making but people are concerned about the ethical problems it may bring when used improperly. Recent work brings the discussion of machine learning fairness into the causal framework and elaborates on the concept of Counterfactual Fairness. In this paper, we develop the Fair Learning through dAta Preprocessing (FLAP) algorithm to learn counterfactually fair decisions from biased training data and formalize the conditions where different data preprocessing procedures should be used to guarantee counterfactual fairness. We also sho…
We study the problem of formally verifying individual fairness of decision tree ensembles, as well as training tree models which maximize both accuracy and individual fairness. In our approach, fairness verification and fairness-aware training both rely on a notion of stability of a classification model, which is a variant of standard robustness under input perturbations used in adversarial machine learning. Our verification and training methods leverage abstract interpretation, a well established technique for static program analysis which is able to automatically infer assertions about stabi…
University of Mannheim（曼海姆大学）；LMU Munich（慕尼黑大学）；University of Maryland（马里兰大学）
The advent of powerful prediction algorithms led to increased automation of high-stake decisions regarding the allocation of scarce resources such as government spending and welfare support. This automation bears the risk of perpetuating unwanted discrimination against vulnerable and historically disadvantaged groups. Research on algorithmic discrimination in computer science and other disciplines developed a plethora of fairness metrics to detect and correct discriminatory algorithms. Drawing on robust sociological and philosophical discourse on distributive justice, we identify the limitatio…
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…
We investigate the fairness concerns of training a machine learning model using data with missing values. Even though there are a number of fairness intervention methods in the literature, most of them require a complete training set as input. In practice, data can have missing values, and data missing patterns can depend on group attributes (e.g. gender or race). Simply applying off-the-shelf fair learning algorithms to an imputed dataset may lead to an unfair model. In this paper, we first theoretically analyze different sources of discrimination risks when training with an imputed dataset. …
Effective complements to human judgment, artificial intelligence techniques have started to aid human decisions in complicated social problems across the world. In the context of United States for instance, automated ML/DL classification models offer complements to human decisions in determining Medicaid eligibility. However, given the limitations in ML/DL model design, these algorithms may fail to leverage various factors for decision making, resulting in improper decisions that allocate resources to individuals who may not be in the most need. In view of such an issue, we propose in this pap…
University of Iowa（爱荷华大学）；University of Texas at Austin（得克萨斯大学奥斯汀分校）
We propose a model-agnostic approach for mitigating the prediction bias of a black-box decision-maker, and in particular, a human decision-maker. Our method detects in the feature space where the black-box decision-maker is biased and replaces it with a few short decision rules, acting as a "fair surrogate". The rule-based surrogate model is trained under two objectives, predictive performance and fairness. Our model focuses on a setting that is common in practice but distinct from other literature on fairness. We only have black-box access to the model, and only a limited set of true labels c…
Missouri University of Science and Technology（密苏里科技大学）
Decision-support systems are information systems that offer support to people's decisions in various applications such as judiciary, real-estate and banking sectors. Lately, these support systems have been found to be discriminatory in the context of many practical deployments. In an attempt to evaluate and mitigate these biases, algorithmic fairness literature has been nurtured using notions of comparative justice, which relies primarily on comparing two/more individuals or groups within the society that is supported by such systems. However, such a fairness notion is not very useful in the i…
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…
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；University of California, Berkeley（加州大学伯克利分校）；Microsoft Research（微软研究院）
As automated decision making and decision assistance systems become common in everyday life, research on the prevention or mitigation of potential harms that arise from decisions made by these systems has proliferated. However, various research communities have independently conceptualized these harms, envisioned potential applications, and proposed interventions. The result is a somewhat fractured landscape of literature focused generally on ensuring decision-making algorithms "do the right thing". In this paper, we compare and discuss work across two major subsets of this literature: algorit…
MPI-SWS（马克斯·普朗克软件系统研究所）；MPI-IS（马克斯·普朗克智能系统研究所）；University of Cambridge（剑桥大学）；Alan Turing Institute（艾伦·图灵研究所）
The adoption of automated, data-driven decision making in an ever expanding range of applications has raised concerns about its potential unfairness towards certain social groups. In this context, a number of recent studies have focused on defining, detecting, and removing unfairness from data-driven decision systems. However, the existing notions of fairness, based on parity (equality) in treatment or outcomes for different social groups, tend to be quite stringent, limiting the overall decision making accuracy. In this paper, we draw inspiration from the fair-division and envy-freeness liter…
