Fairness of Machine Learning Algorithms in Demography
National Research University Higher School of Economics（俄罗斯高等经济大学国立研究型大学（莫斯科））；Moscow（莫斯科（注：此处“Moscow”为城市名，按要求不提取，但原机构名已包含，需保留））；HSE（高等经济大学（注：HSE为原机构缩写，与“National Research University Higher School of Economics”为同一机构，按要求提取到大学级别即可））
Ibe Chukwuemeka Emmanuel, Ekaterina Mitrofanova
备注：
This is an empirical replication study but with other demographic data. The theory and method description is heavily based on the arXiv:2006.10531
The paper is devoted to the study of the model fairness and process fairness of the Russian demographic dataset by making predictions of divorce of the 1st marriage, religiosity, 1st employment and completion of education. Our goal was to make classifiers more equitable by reducing their reliance on sensitive features while increasing or at least maintaining their accuracy. We took inspiration from "dropout" techniques in neural-based approaches and suggested a model that uses "feature drop-out" to address process fairness. To evaluate a classifier's fairness and decide the sensitive features to eliminate, we used "LIME Explanations". This results in a pool of classifiers due to feature dropout whose ensemble has been shown to be less reliant on sensitive features and to have improved or no effect on accuracy. Our empirical study was performed on four families of classifiers (Logistic Regression, Random Forest, Bagging, and Adaboost) and carried out on real-life dataset (Russian demographic data derived from Generations and Gender Survey), and it showed that all of the models became less dependent on sensitive features (such as gender, breakup of the 1st partnership, 1st partnership, etc.) and showed improvements or no impact on accuracy
As machine learning (ML) systems get adopted in more critical areas, it has become increasingly crucial to address the bias that could occur in these systems. Several fairness pre-processing algorithms are available to alleviate implicit biases during model training. These algorithms employ different concepts of fairness, often leading to conflicting strategies with consequential trade-offs between fairness and accuracy. In this work, we evaluate three popular fairness pre-processing algorithms and investigate the potential for combining all algorithms into a more robust pre-processing ensembl…
Long-Term Fairness Inquiries and Pursuits in Machine Learning: A Survey of Notions, Methods, and Challenges
Iowa State University（爱荷华州立大学）；Carnegie Mellon University（卡内基梅隆大学）；University of California, Santa Cruz（加州大学圣克鲁兹分校）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）
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 …
Bias in machine learning has manifested injustice in several areas, such as medicine, hiring, and criminal justice. In response, computer scientists have developed myriad definitions of fairness to correct this bias in fielded algorithms. While some definitions are based on established legal and ethical norms, others are largely mathematical. It is unclear whether the general public agrees with these fairness definitions, and perhaps more importantly, whether they understand these definitions. We take initial steps toward bridging this gap between ML researchers and the public, by addressing t…
Fairness-aware machine learning (fair-ml) techniques are algorithmic interventions designed to ensure that individuals who are affected by the predictions of a machine learning model are treated fairly. The problem is often posed as an optimization problem, where the objective is to achieve high predictive performance under a quantitative fairness constraint. However, any attempt to design a fair-ml algorithm must assume a world where Goodhart's law has an exception: when a fairness measure becomes an optimization constraint, it does not cease to be a good measure. In this paper, we argue that…
Quantitative definitions of what is unfair and what is fair have been introduced in multiple disciplines for well over 50 years, including in education, hiring, and machine learning. We trace how the notion of fairness has been defined within the testing communities of education and hiring over the past half century, exploring the cultural and social context in which different fairness definitions have emerged. In some cases, earlier definitions of fairness are similar or identical to definitions of fairness in current machine learning research, and foreshadow current formal work. In other cas…
University of Tübingen（图宾根大学）；Tübingen AI Centre（图宾根人工智能中心）
Fair Machine Learning endeavors to prevent unfairness arising in the context of machine learning applications embedded in society. Despite the variety of definitions of fairness and proposed "fair algorithms", there remain unresolved conceptual problems regarding fairness. In this paper, we dissect the role of statistical independence in fairness and randomness notions regularly used in machine learning. Thereby, we are led to a suprising hypothesis: randomness and fairness can be considered equivalent concepts in machine learning. In particular, we obtain a relativized notion of randomness ex…
IBM Research（IBM研究院）；Massachusetts Institute of Technology（麻省理工学院）
Mitigating algorithmic bias is a critical task in the development and deployment of machine learning models. While several toolkits exist to aid machine learning practitioners in addressing fairness issues, little is known about the strategies practitioners employ to evaluate model fairness and what factors influence their assessment, particularly in the context of text classification. Two common approaches of evaluating the fairness of a model are group fairness and individual fairness. We run a study with Machine Learning practitioners (n=24) to understand the strategies used to evaluate mod…
Over the past several years, a slew of different methods to measure the fairness of a machine learning model have been proposed. However, despite the growing number of publications and implementations, there is still a critical lack of literature that explains the interplay of fair machine learning with the social sciences of philosophy, sociology, and law. We hope to remedy this issue by accumulating and expounding upon the thoughts and discussions of fair machine learning produced by both social and formal (specifically machine learning and statistics) sciences in this field guide. Specifica…
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…
Université du Québec à Montréal（魁北克大学蒙特利尔分校）；Higher Colleges of Technology（高等技术学院）；Inria（法国国家信息与自动化研究所）；Ecole Polytechnique（巴黎综合理工学院）；IPP（巴黎理工学院）
Fairness emerged as an important requirement to guarantee that Machine Learning (ML) predictive systems do not discriminate against specific individuals or entire sub-populations, in particular, minorities. Given the inherent subjectivity of viewing the concept of fairness, several notions of fairness have been introduced in the literature. This paper is a survey that illustrates the subtleties between fairness notions through a large number of examples and scenarios. In addition, unlike other surveys in the literature, it addresses the question of: which notion of fairness is most suited to a…
KenSci Inc（KenSci公司）；University of Washington - Tacoma（华盛顿大学塔科马分校）；University of Washington - Bothell（华盛顿大学博塞尔分校）
Fairness in AI and machine learning systems has become a fundamental problem in the accountability of AI systems. While the need for accountability of AI models is near ubiquitous, healthcare in particular is a challenging field where accountability of such systems takes upon additional importance, as decisions in healthcare can have life altering consequences. In this paper we present preliminary results on fairness in the context of classification parity in healthcare. We also present some exploratory methods to improve fairness and choosing appropriate classification algorithms in the conte…
The fairness of machine learning-based decisions has become an increasingly important focus in the design of supervised machine learning methods. Most fairness approaches optimize a specified trade-off between performance measure(s) (e.g., accuracy, log loss, or AUC) and fairness metric(s) (e.g., demographic parity, equalized odds). This begs the question: are the right performance-fairness trade-offs being specified? We instead re-cast fair machine learning as an imitation learning task by introducing superhuman fairness, which seeks to simultaneously outperform human decisions on multiple pr…
National University of Singapore（新加坡国立大学）；Institute for Infocomm Research, A*STAR（资讯通信研究院，新加坡科技研究局）
The Shapley value (SV) is adopted in various scenarios in machine learning (ML), including data valuation, agent valuation, and feature attribution, as it satisfies their fairness requirements. However, as exact SVs are infeasible to compute in practice, SV estimates are approximated instead. This approximation step raises an important question: do the SV estimates preserve the fairness guarantees of exact SVs? We observe that the fairness guarantees of exact SVs are too restrictive for SV estimates. Thus, we generalise Shapley fairness to probably approximate Shapley fairness and propose fide…
University of California, Irvine（加州大学欧文分校）；Centers for Disease Control and Prevention（美国疾病控制与预防中心）
Applying standard machine learning approaches for classification can produce unequal results across different demographic groups. When then used in real-world settings, these inequities can have negative societal impacts. This has motivated the development of various approaches to fair classification with machine learning models in recent years. In this paper, we consider the problem of modifying the predictions of a blackbox machine learning classifier in order to achieve fairness in a multiclass setting. To accomplish this, we extend the 'post-processing' approach in Hardt et al. 2016, which…
Carnegie Mellon University（卡内基梅隆大学）；University of Cambridge（剑桥大学）
Recent years have seen the development of many open-source ML fairness toolkits aimed at helping ML practitioners assess and address unfairness in their systems. However, there has been little research investigating how ML practitioners actually use these toolkits in practice. In this paper, we conducted the first in-depth empirical exploration of how industry practitioners (try to) work with existing fairness toolkits. In particular, we conducted think-aloud interviews to understand how participants learn about and use fairness toolkits, and explored the generality of our findings through an …
An Experimental Study on Fairness-aware Machine Learning for Credit Scoring Problems
Banking Academy of Vietnam（越南银行学院）；Vietnam Academy of Science and Technology（越南科学技术 academy）；Hanoi University of Science and Technology（河内科学技术大学）；University of Koblenz（科隆大学）
Tel-Aviv University（特拉维夫大学）；The Open University（开放大学）
The performance of machine learning algorithms can be considerably improved when trained over larger datasets. In many domains, such as medicine and finance, larger datasets can be obtained if several parties, each having access to limited amounts of data, collaborate and share their data. However, such data sharing introduces significant privacy challenges. While multiple recent studies have investigated methods for private collaborative machine learning, the fairness of such collaborative algorithms was overlooked. In this work we suggest a feasible privacy-preserving pre-process mechanism f…
FAIREDU: A Multiple Regression-Based Method for Enhancing Fairness in Machine Learning Models for Educational Applications
Dainam University（大南大学）；VNU University of Engineering and Technology（越南国家大学工程技术大学）；Latrobe University（拉筹伯大学）；University of South Eastern Norway（东南挪威大学）
Criminal recidivism models are tools that have gained widespread adoption by parole boards across the United States to assist with parole decisions. These models take in large amounts of data about an individual and then predict whether an individual would commit a crime if released on parole. Although such models are not the only or primary factor in making the final parole decision, questions have been raised about their accuracy, fairness, and interpretability. In this paper, various machine learning-based criminal recidivism models are created based on a real-world parole decision dataset …
Department of Computer Science, Montanuniversitat Leoben（蒙塔努大学莱奥本分校计算机科学系）；Department of Computer Science, TU Eindhoven（埃因霍温理工大学计算机科学系）
Machine learning algorithms for prediction are increasingly being used in critical decisions affecting human lives. Various fairness formalizations, with no firm consensus yet, are employed to prevent such algorithms from systematically discriminating against people based on certain attributes protected by law. The aim of this article is to survey how fairness is formalized in the machine learning literature for the task of prediction and present these formalizations with their corresponding notions of distributive justice from the social sciences literature. We provide theoretical as well as …
In the ML fairness literature, there have been few investigations through the viewpoint of philosophy, a lens that encourages the critical evaluation of basic assumptions. The purpose of this paper is to use three ideas from the philosophy of science and computer science to tease out blind spots in the assumptions that underlie ML fairness: abstraction, induction, and measurement. Through this investigation, we hope to warn of these methodological blind spots and encourage further interdisciplinary investigation in fair-ML through the framework of philosophy.
University of Cambridge（剑桥大学）；MRC Biostatistics Unit, University of Cambridge（剑桥大学医学研究委员会生物统计组）；Sapienza University of Rome（罗马第一大学）；The Alan Turing Institute（阿兰·图灵研究所）；Technical University of Munich（慕尼黑工业大学）；Helmholtz Munich（亥姆霍兹慕尼黑中心）
While interest in the application of machine learning to improve healthcare has grown tremendously in recent years, a number of barriers prevent deployment in medical practice. A notable concern is the potential to exacerbate entrenched biases and existing health disparities in society. The area of fairness in machine learning seeks to address these issues of equity; however, appropriate approaches are context-dependent, necessitating domain-specific consideration. We focus on clinical trials, i.e., research studies conducted on humans to evaluate medical treatments. Clinical trials are a rela…
Across machine learning (ML) sub-disciplines, researchers make explicit mathematical assumptions in order to facilitate proof-writing. We note that, specifically in the area of fairness-accuracy trade-off optimization scholarship, similar attention is not paid to the normative assumptions that ground this approach. Such assumptions presume that 1) accuracy and fairness are in inherent opposition to one another, 2) strict notions of mathematical equality can adequately model fairness, 3) it is possible to measure the accuracy and fairness of decisions independent from historical context, and 4)…
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…
Leibniz University Hannover（汉诺威莱布尼茨大学）；Carnegie Mellon University（卡内基梅隆大学）；Free University Berlin（柏林自由大学）
As decision-making increasingly relies on Machine Learning (ML) and (big) data, the issue of fairness in data-driven Artificial Intelligence (AI) systems is receiving increasing attention from both research and industry. A large variety of fairness-aware machine learning solutions have been proposed which involve fairness-related interventions in the data, learning algorithms and/or model outputs. However, a vital part of proposing new approaches is evaluating them empirically on benchmark datasets that represent realistic and diverse settings. Therefore, in this paper, we overview real-world …
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…
What is Fair? Defining Fairness in Machine Learning for Health
Department of Statistical Sciences, University of Toronto（统计科学系，多伦多大学）；Harvard T.H. Chan School of Public Health（哈佛T.H. Chan公共卫生学院）；York University（约克大学）；Verily Life Sciences（Verily生命科学公司）；Duke University（杜克大学）；University of Toronto（多伦多大学）
In recent years, many incidents have been reported where machine learning models exhibited discrimination among people based on race, sex, age, etc. Research has been conducted to measure and mitigate unfairness in machine learning models. For a machine learning task, it is a common practice to build a pipeline that includes an ordered set of data preprocessing stages followed by a classifier. However, most of the research on fairness has considered a single classifier based prediction task. What are the fairness impacts of the preprocessing stages in machine learning pipeline? Furthermore, st…
MIT（麻省理工学院）；MIT-IBM Watson AI Lab, IBM Research（麻省理工-IBM 沃森人工智能实验室，IBM研究院）
As machine learning algorithms grow in popularity and diversify to many industries, ethical and legal concerns regarding their fairness have become increasingly relevant. We explore the problem of algorithmic fairness, taking an information-theoretic view. The maximal correlation framework is introduced for expressing fairness constraints and shown to be capable of being used to derive regularizers that enforce independence and separation-based fairness criteria, which admit optimization algorithms for both discrete and continuous variables which are more computationally efficient than existin…
AdapFair: Ensuring Adaptive Fairness for Machine Learning Operations
Department of Information Systems and Intelligent Business, School of Management, Xi’an Jiaotong University（信息系统与智能商业系，管理学院，西安交通大学）；School of Statistics and Data Science, Shanghai University of Finance and Economics（统计与数据科学学院，上海财经大学）
