Although several fairness definitions and bias mitigation techniques exist in the literature, all existing solutions evaluate fairness of Machine Learning (ML) systems after the training stage. In this paper, we take the first steps towards evaluating a more holistic approach by testing for fairness both before and after model training. We evaluate the effectiveness of the proposed approach and position it within the ML development lifecycle, using an empirical analysis of the relationship between model dependent and independent fairness metrics. The study uses 2 fairness metrics, 4 ML algorithms, 5 real-world datasets and 1600 fairness evaluation cycles. We find a linear relationship between data and model fairness metrics when the distribution and the size of the training data changes. Our results indicate that testing for fairness prior to training can be a ``cheap'' and effective means of catching a biased data collection process early; detecting data drifts in production systems and minimising execution of full training cycles thus reducing development time and costs.
The applications of Artificial Intelligence (AI) surround decisions on increasingly many aspects of human lives. Society responds by imposing legal and social expectations for the accountability of such automated decision systems (ADSs). Fairness, a fundamental constituent of AI accountability, is concerned with just treatment of individuals and sensitive groups (e.g., based on sex, race). While many studies focus on fair learning and fairness testing for the classification tasks, the literature is rather limited on how to examine fairness in regression tasks. This work presents error parity a…
Microsoft Research Lab Asia（微软亚洲研究院）；University College London（伦敦大学学院）；The University of Newcastle（纽卡斯尔大学）
Fairness testing aims at mitigating unintended discrimination in the decision-making process of data-driven AI systems. Individual discrimination may occur when an AI model makes different decisions for two distinct individuals who are distinguishable solely according to protected attributes, such as age and race. Such instances reveal biased AI behaviour, and are called Individual Discriminatory Instances (IDIs). In this paper, we propose an approach for the selection of the initial seeds to generate IDIs for fairness testing. Previous studies mainly used random initial seeds to this end. How…
Testing machine learning software for ethical bias has become a pressing current concern. In response, recent research has proposed a plethora of new fairness metrics, for example, the dozens of fairness metrics in the IBM AIF360 toolkit. This raises the question: How can any fairness tool satisfy such a diverse range of goals? While we cannot completely simplify the task of fairness testing, we can certainly reduce the problem. This paper shows that many of those fairness metrics effectively measure the same thing. Based on experiments using seven real-world datasets, we find that (a) 26 clas…
Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg（卢森堡大学安全、可靠性与信任跨学科中心）；Singapore University of Technology and Design（新加坡科技设计大学）
Software often produces biased outputs. In particular, machine learning (ML) based software are known to produce erroneous predictions when processing discriminatory inputs. Such unfair program behavior can be caused by societal bias. In the last few years, Amazon, Microsoft and Google have provided software services that produce unfair outputs, mostly due to societal bias (e.g. gender or race). In such events, developers are saddled with the task of conducting fairness testing. Fairness testing is challenging; developers are tasked with generating discriminatory inputs that reveal and explain…
As deep image classification applications, e.g., face recognition, become increasingly prevalent in our daily lives, their fairness issues raise more and more concern. It is thus crucial to comprehensively test the fairness of these applications before deployment. Existing fairness testing methods suffer from the following limitations: 1) applicability, i.e., they are only applicable for structured data or text without handling the high-dimensional and abstract domain sampling in the semantic level for image classification applications; 2) functionality, i.e., they generate unfair samples with…
University of Arkansas（阿肯色大学）；University of Illinois（伊利诺伊大学）
Federated learning is an emerging framework that builds centralized machine learning models with training data distributed across multiple devices. Most of the previous works about federated learning focus on the privacy protection and communication cost reduction. However, how to achieve fairness in federated learning is under-explored and challenging especially when testing data distribution is different from training distribution or even unknown. Introducing simple fairness constraints on the centralized model cannot achieve model fairness on unknown testing data. In this paper, we develop …
Stanford University（斯坦福大学）；Singapore University of Technology and Design（新加坡科技设计大学）；VinAI Research（VinAI研究院）
We present a statistical testing framework to detect if a given machine learning classifier fails to satisfy a wide range of group fairness notions. The proposed test is a flexible, interpretable, and statistically rigorous tool for auditing whether exhibited biases are intrinsic to the algorithm or due to the randomness in the data. The statistical challenges, which may arise from multiple impact criteria that define group fairness and which are discontinuous on model parameters, are conveniently tackled by projecting the empirical measure onto the set of group-fair probability models using o…
University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）
This paper defines software fairness and discrimination and develops a testing-based method for measuring if and how much software discriminates, focusing on causality in discriminatory behavior. Evidence of software discrimination has been found in modern software systems that recommend criminal sentences, grant access to financial products, and determine who is allowed to participate in promotions. Our approach, Themis, generates efficient test suites to measure discrimination. Given a schema describing valid system inputs, Themis generates discrimination tests automatically and does not req…
Wasserstein projection distance for fairness testing of regression models
Department of Computer Science, University of British Columbia（计算机科学系，不列颠哥伦比亚大学）；Department of Pathology and Laboratory Medicine, University of British Columbia（病理学与实验室医学系，不列颠哥伦比亚大学）；Department of Statistics, University of British Columbia（统计学系，不列颠哥伦比亚大学）；BC Cancer Research, Part of Provincial Health Care Authority（BC癌症研究，省卫生保健机构的一部分）；Department of Mathematics, University of British Columbia（数学系，不列颠哥伦比亚大学）
Zhejiang University（浙江大学）；Singapore Management University（新加坡管理大学）；Huawei International Pte. Ltd.（华为国际私人有限公司）；National University of Singapore（新加坡国立大学）
Although deep learning has demonstrated astonishing performance in many applications, there are still concerns about its dependability. One desirable property of deep learning applications with societal impact is fairness (i.e., non-discrimination). Unfortunately, discrimination might be intrinsically embedded into the models due to the discrimination in the training data. As a countermeasure, fairness testing systemically identifies discriminatory samples, which can be used to retrain the model and improve the model's fairness. Existing fairness testing approaches however have two major limit…
Machine learning models are vulnerable to biases that result in unfair treatment of individuals from different populations. Recent work that aims to test a model's fairness at the individual level either relies on domain knowledge to choose metrics, or on input transformations that risk generating out-of-domain samples. We describe a new approach for testing individual fairness that does not have either requirement. We propose a novel criterion for evaluating individual fairness and develop a practical testing method based on this criterion which we call fAux (pronounced fox). This is based on…
The fairness characteristic is a critical attribute of trusted AI systems. A plethora of research has proposed diverse methods for individual fairness testing. However, they are suffering from three major limitations, i.e., low efficiency, low effectiveness, and model-specificity. This work proposes ExpGA, an explanationguided fairness testing approach through a genetic algorithm (GA). ExpGA employs the explanation results generated by interpretable methods to collect high-quality initial seeds, which are prone to derive discriminatory samples by slightly modifying feature values. ExpGA then a…
Discrimination has been shown in many machine learning applications, which calls for sufficient fairness testing before their deployment in ethic-relevant domains such as face recognition, medical diagnosis and criminal sentence. Existing fairness testing approaches are mostly designed for identifying individual discrimination, i.e., discrimination against individuals. Yet, as another widely concerning type of discrimination, testing against group discrimination, mostly hidden, is much less studied. To address the gap, in this work, we propose TESTSGD, an interpretable testing approach which s…
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…
University of Texas at El Paso（得克萨斯大学埃尔帕索分校）；Pennsylvania State University（宾夕法尼亚州立大学）；University of Colorado Boulder（科罗拉多大学博尔德分校）
This paper investigates the parameter space of machine learning (ML) algorithms in aggravating or mitigating fairness bugs. Data-driven software is increasingly applied in social-critical applications where ensuring fairness is of paramount importance. The existing approaches focus on addressing fairness bugs by either modifying the input dataset or modifying the learning algorithms. On the other hand, the selection of hyperparameters, which provide finer controls of ML algorithms, may enable a less intrusive approach to influence the fairness. Can hyperparameters amplify or suppress discrimin…
Zhejiang University of Technology（浙江工业大学）；Zhejiang University（浙江大学）；Huawei International Pte. Ltd.（华为国际有限公司）；National University of Defense Technology（国防科技大学）
Deep neural networks (DNNs) have demonstrated their outperformance in various domains. However, it raises a social concern whether DNNs can produce reliable and fair decisions especially when they are applied to sensitive domains involving valuable resource allocation, such as education, loan, and employment. It is crucial to conduct fairness testing before DNNs are reliably deployed to such sensitive domains, i.e., generating as many instances as possible to uncover fairness violations. However, the existing testing methods are still limited from three aspects: interpretability, performance, …
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.
Singapore Univ. of Tech. and Design（新加坡科技设计大学）；BITS Pilani（皮拉尼博拉理工学院）
Fairness is a critical trait in decision making. As machine-learning models are increasingly being used in sensitive application domains (e.g. education and employment) for decision making, it is crucial that the decisions computed by such models are free of unintended bias. But how can we automatically validate the fairness of arbitrary machine-learning models? For a given machine-learning model and a set of sensitive input parameters, our AEQUITAS approach automatically discovers discriminatory inputs that highlight fairness violation. At the core of AEQUITAS are three novel strategies to em…
IBM Research（IBM研究院）；Carnegie Mellon University（卡内基梅隆大学）
A trade-off between accuracy and fairness is almost taken as a given in the existing literature on fairness in machine learning. Yet, it is not preordained that accuracy should decrease with increased fairness. Novel to this work, we examine fair classification through the lens of mismatched hypothesis testing: trying to find a classifier that distinguishes between two ideal distributions when given two mismatched distributions that are biased. Using Chernoff information, a tool in information theory, we theoretically demonstrate that, contrary to popular belief, there always exist ideal distr…
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 bou…
University of Texas at El Paso（德克萨斯大学埃尔帕索分校）；Virginia Tech（弗吉尼亚理工大学）；Austin Peay State University（奥斯汀佩伊州立大学）
In this research, we focus on the usage of adversarial sampling to test for the fairness in the prediction of deep neural network model across different classes of image in a given dataset. While several framework had been proposed to ensure robustness of machine learning model against adversarial attack, some of which includes adversarial training algorithm. There is still the pitfall that adversarial training algorithm tends to cause disparity in accuracy and robustness among different group. Our research is aimed at using adversarial sampling to test for fairness in the prediction of deep n…
Rice University（莱斯大学）；University of Florida（佛罗里达大学）
Algorithmic fairness has emerged as an important consideration when using machine learning to make high-stakes societal decisions. Yet, improved fairness often comes at the expense of model accuracy. While aspects of the fairness-accuracy tradeoff have been studied, most work reports the fairness and accuracy of various models separately; this makes model comparisons nearly impossible without a model-agnostic metric that reflects the balance of the two desiderata. We seek to identify, quantify, and optimize the empirical Pareto frontier of the fairness-accuracy tradeoff. Specifically, we ident…
University of Cambridge（剑桥大学）；The Alan Turing Institute（艾伦·图灵研究所）
The notion of individual fairness requires that similar people receive similar treatment. However, this is hard to achieve in practice since it is difficult to specify the appropriate similarity metric. In this work, we attempt to learn such similarity metric from human annotated data. We gather a new dataset of human judgments on a criminal recidivism prediction (COMPAS) task. By assuming the human supervision obeys the principle of individual fairness, we leverage prior work on metric learning, evaluate the performance of several metric learning methods on our dataset, and show that the lear…
Istituto Italiano di Tecnologia（意大利理工学院）；University of Genova（热那亚大学）；University of Waterloo（滑铁卢大学）；University College London（伦敦大学学院）
We address the problem of algorithmic fairness: ensuring that sensitive variables do not unfairly influence the outcome of a classifier. We present an approach based on empirical risk minimization, which incorporates a fairness constraint into the learning problem. It encourages the conditional risk of the learned classifier to be approximately constant with respect to the sensitive variable. We derive both risk and fairness bounds that support the statistical consistency of our approach. We specify our approach to kernel methods and observe that the fairness requirement implies an orthogonali…
Machine learning models are increasingly being used in important decision-making software such as approving bank loans, recommending criminal sentencing, hiring employees, and so on. It is important to ensure the fairness of these models so that no discrimination is made based on protected attribute (e.g., race, sex, age) while decision making. Algorithms have been developed to measure unfairness and mitigate them to a certain extent. In this paper, we have focused on the empirical evaluation of fairness and mitigations on real-world machine learning models. We have created a benchmark of 40 t…
Testing autonomous vehicles and AI: perspectives and challenges from cybersecurity, transparency, robustness and fairness
European Commission, Joint Research Centre（欧盟委员会联合研究中心）；University of Alcalá（阿尔卡拉大学）；EPFL - Swiss Federal Institute of Technology（瑞士洛桑联邦理工学院）；University of Oxford（牛津大学）；BASt - German Federal Highway Research Institute（德国联邦公路研究所）；Reed Mobility（里德移动公司）
University of Pennsylvania（宾夕法尼亚大学）；University of Minnesota（明尼苏达大学）
Kearns et al. [2018] recently proposed a notion of rich subgroup fairness intended to bridge the gap between statistical and individual notions of fairness. Rich subgroup fairness picks a statistical fairness constraint (say, equalizing false positive rates across protected groups), but then asks that this constraint hold over an exponentially or infinitely large collection of subgroups defined by a class of functions with bounded VC dimension. They give an algorithm guaranteed to learn subject to this constraint, under the condition that it has access to oracles for perfectly learning absent …
We present FlipTest, a black-box technique for uncovering discrimination in classifiers. FlipTest is motivated by the intuitive question: had an individual been of a different protected status, would the model have treated them differently? Rather than relying on causal information to answer this question, FlipTest leverages optimal transport to match individuals in different protected groups, creating similar pairs of in-distribution samples. We show how to use these instances to detect discrimination by constructing a "flipset": the set of individuals whose classifier output changes post-tra…
Singapore University of Technology and Design（新加坡科技设计大学）
Automatic Speech Recognition (ASR) systems have become ubiquitous. They can be found in a variety of form factors and are increasingly important in our daily lives. As such, ensuring that these systems are equitable to different subgroups of the population is crucial. In this paper, we introduce, AequeVox, an automated testing framework for evaluating the fairness of ASR systems. AequeVox simulates different environments to assess the effectiveness of ASR systems for different populations. In addition, we investigate whether the chosen simulations are comprehensible to humans. We further propo…
Looking Beyond What You See: An Empirical Analysis on Subgroup Intersectional Fairness for Multi-label Chest X-ray Classification Using Social Determinants of Racial Health Inequities
Massachusetts Institute of Technology（麻省理工学院）；University at Buffalo（布法罗大学）
Causal Pre-training Under the Fairness Lens: An Empirical Study of TabPFN
University of Bergen Centre for the Science of Learning \& Technology (SLATE) Bergen Norway；Department of Computer Science University of Oxford；Alan Turing Institute Oxford United Kingdom；University of Bergen；University of Oxford；Alan Turing Institute
Algorithm fairness in the application of artificial intelligence (AI) is essential for a better society. As the foundational axiom of social mechanisms, fairness consists of multiple facets. Although the machine learning (ML) community has focused on intersectionality as a matter of statistical parity, especially in discrimination issues, an emerging body of literature addresses another facet -- monotonicity. Based on domain expertise, monotonicity plays a vital role in numerous fairness-related areas, where violations could misguide human decisions and lead to disastrous consequences. In this…
University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Colleges and universities use predictive analytics in a variety of ways to increase student success rates. Despite the potential for predictive analytics, two major barriers exist to their adoption in higher education: (a) the lack of democratization in deployment, and (b) the potential to exacerbate inequalities. Education researchers and policymakers encounter numerous challenges in deploying predictive modeling in practice. These challenges present in different steps of modeling including data preparation, model development, and evaluation. Nevertheless, each of these steps can introduce ad…
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…
Carnegie Mellon University（卡内基梅隆大学）；University of Minnesota（明尼苏达大学）
Motivated by the growing importance of reducing unfairness in ML predictions, Fair-ML researchers have presented an extensive suite of algorithmic 'fairness-enhancing' remedies. Most existing algorithms, however, are agnostic to the sources of the observed unfairness. As a result, the literature currently lacks guiding frameworks to specify conditions under which each algorithmic intervention can potentially alleviate the underpinning cause of unfairness. To close this gap, we scrutinize the underlying biases (e.g., in the training data or design choices) that cause observational unfairness. W…
University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；California Institute of Technology（加州理工学院）
Making predictions that are fair with regard to protected group membership (race, gender, age, etc.) has become an important requirement for classification algorithms. Existing techniques derive a fair model from sampled labeled data relying on the assumption that training and testing data are identically and independently drawn (iid) from the same distribution. In practice, distribution shift can and does occur between training and testing datasets as the characteristics of individuals interacting with the machine learning system change. We investigate fairness under covariate shift, a relaxa…
