AI fairness measurements, including tests for equal treatment, often take the form of disaggregated evaluations of AI systems. Such measurements are an important part of Responsible AI operations. These measurements compare system performance across demographic groups or sub-populations and typically require member-level demographic signals such as gender, race, ethnicity, and location. However, sensitive member-level demographic attributes like race and ethnicity can be challenging to obtain and use due to platform choices, legal constraints, and cultural norms. In this paper, we focus on the task of enabling AI fairness measurements on race/ethnicity for \emph{U.S. LinkedIn members} in a privacy-preserving manner. We present the Privacy-Preserving Probabilistic Race/Ethnicity Estimation (PPRE) method for performing this task. PPRE combines the Bayesian Improved Surname Geocoding (BISG) model, a sparse LinkedIn survey sample of self-reported demographics, and privacy-enhancing technologies like secure two-party computation and differential privacy to enable meaningful fairness measurements while preserving member privacy. We provide details of the PPRE method and its privacy guarantees. We then illustrate sample measurement operations. We conclude with a review of open research and engineering challenges for expanding our privacy-preserving fairness measurement capabilities.
Jeb E. Brooks School of Public Policy（杰布·E·布鲁克斯公共政策学院）；Cornell University（康奈尔大学）
Bayesian Improved Surname Geocoding (BISG) is the most popular method for proxying race/ethnicity in voter registration files that do not contain it. This paper benchmarks BISG against a range of previously untested machine learning alternatives, using voter files with self-reported race/ethnicity from California, Florida, North Carolina, and Georgia. This analysis yields three key findings. First, machine learning consistently outperforms BISG at individual classification of race/ethnicity. Second, BISG and machine learning methods exhibit divergent biases for estimating regional racial compo…
This paper presents raceBERT -- a transformer-based model for predicting race and ethnicity from character sequences in names, and an accompanying python package. Using a transformer-based model trained on a U.S. Florida voter registration dataset, the model predicts the likelihood of a name belonging to 5 U.S. census race categories (White, Black, Hispanic, Asian & Pacific Islander, American Indian & Alaskan Native). I build on Sood and Laohaprapanon (2018) by replacing their LSTM model with transformer-based models (pre-trained BERT model, and a roBERTa model trained from scratch), and compa…
Princeton University（普林斯顿大学）；King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学）；University of Chicago（芝加哥大学）
Anonymized electronic medical records are an increasingly popular source of research data. However, these datasets often lack race and ethnicity information. This creates problems for researchers modeling human disease, as race and ethnicity are powerful confounders for many health exposures and treatment outcomes; race and ethnicity are closely linked to population-specific genetic variation. We showed that deep neural networks generate more accurate estimates for missing racial and ethnic information than competing methods (e.g., logistic regression, random forest). RIDDLE yielded significan…
Harvard University（哈佛大学）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
We provide the largest compiled publicly available dictionaries of first, middle, and last names for the purpose of imputing race and ethnicity using, for example, Bayesian Improved Surname Geocoding (BISG). The dictionaries are based on the voter files of six Southern states that collect self-reported racial data upon voter registration. Our data cover a much larger scope of names than any comparable dataset, containing roughly one million first names, 1.1 million middle names, and 1.4 million surnames. Individuals are categorized into five mutually exclusive racial and ethnic groups -- White…
Although prediction models for delirium, a commonly occurring condition during general hospitalization or post-surgery, have not gained huge popularity, their algorithmic bias evaluation is crucial due to the existing association between social determinants of health and delirium risk. In this context, using MIMIC-III and another academic hospital dataset, we present some initial experimental evidence showing how sociodemographic features such as sex and race can impact the model performance across subgroups. With this work, our intent is to initiate a discussion about the intersectionality ef…
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…
Debias-CLR: A Contrastive Learning Based Debiasing Method for Algorithmic Fairness in Healthcare Applications
Wright State University（莱特州立大学）；Cincinnati Children’s Hospital Medical Center（辛辛那提儿童医院医疗中心）；Kairos Research LLC（Kairos Research有限责任公司）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）
Stanford University（斯坦福大学）；Stanford Institute for Economic Policy Research（斯坦福经济政策研究所）；Stanford Institute for Human-Centered Artificial Intelligence（斯坦福以人为本人工智能研究所）；Partnership on AI（人工智能伙伴关系）
While there has been a flurry of research in algorithmic fairness, what is less recognized is that modern antidiscrimination law may prohibit the adoption of such techniques. We make three contributions. First, we discuss how such approaches will likely be deemed "algorithmic affirmative action," posing serious legal risks of violating equal protection, particularly under the higher education jurisprudence. Such cases have increasingly turned toward anticlassification, demanding "individualized consideration" and barring formal, quantitative weights for race regardless of purpose. This case la…
Equity of educational outcome and fairness of AI with respect to race have been topics of increasing importance in education. In this work, we address both with empirical evaluations of grade prediction in higher education, an important task to improve curriculum design, plan interventions for academic support, and offer course guidance to students. With fairness as the aim, we trial several strategies for both label and instance balancing to attempt to minimize differences in algorithm performance with respect to race. We find that an adversarial learning approach, combined with grade label b…
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…
An Algorithmic Approach for Causal Health Equity: A Look at Race Differentials in Intensive Care Unit (ICU) Outcomes
Columbia University（哥伦比亚大学）；Flinders University（弗林德斯大学）；University of Melbourne（墨尔本大学）；Technical University of Munich（慕尼黑工业大学）；Prince Charles Hospital Brisbane（布里斯班查尔斯王子医院）；Edith Cowan University（伊迪丝·考恩大学）；Monash University（莫纳什大学）；Massachusetts Institute of Technology（麻省理工学院）
Stevens Institute of Technology（史蒂文斯理工学院）；Rutgers University（罗格斯大学）
While predictive policing has become increasingly common in assisting with decisions in the criminal justice system, the use of these results is still controversial. Some software based on deep learning lacks accuracy (e.g., in F-1), and importantly many decision processes are not transparent, causing doubt about decision bias, such as perceived racial and age disparities. This paper addresses bias issues with post-hoc explanations to provide a trustable prediction of whether a person will receive future criminal charges given one's previous criminal records by learning temporal behavior patte…
DeepMind；Centre for Artificial Intelligence, University College London（伦敦大学学院人工智能中心）
Advances in algorithmic fairness have largely omitted sexual orientation and gender identity. We explore queer concerns in privacy, censorship, language, online safety, health, and employment to study the positive and negative effects of artificial intelligence on queer communities. These issues underscore the need for new directions in fairness research that take into account a multiplicity of considerations, from privacy preservation, context sensitivity and process fairness, to an awareness of sociotechnical impact and the increasingly important role of inclusive and participatory research …
Human Rights Data Analysis Group（人权数据分析组织）；Stanford University（斯坦福大学）
Predictive modeling is increasingly being employed to assist human decision-makers. One purported advantage of replacing human judgment with computer models in high stakes settings-- such as sentencing, hiring, policing, college admissions, and parole decisions-- is the perceived "neutrality" of computers. It is argued that because computer models do not hold personal prejudice, the predictions they produce will be equally free from prejudice. There is growing recognition that employing algorithms does not remove the potential for bias, and can even amplify it, since training data were inevita…
Supervised Algorithmic Fairness in Distribution Shifts: A Survey
School of New Media and Communication, Tianjin University（天津大学新媒体与传播学院）；College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；Department of Computer Science, Baylor University（贝勒大学计算机系）；Electrical Engineering and Computer Science Department, University of Arkansas（阿肯色大学电气与计算机科学系）
Disease identification is a core, routine activity in observational health research. Cohorts impact downstream analyses, such as how a condition is characterized, how patient risk is defined, and what treatments are studied. It is thus critical to ensure that selected cohorts are representative of all patients, independently of their demographics or social determinants of health. While there are multiple potential sources of bias when constructing phenotype definitions which may affect their fairness, it is not standard in the field of phenotyping to consider the impact of different definition…
