Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency最新文献_第10页

Assessing algorithmic fairness with unobserved protected class using data combination 使用数据组合评估未观察到的受保护类的算法公平性

Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency Pub Date : 2019-06-01 DOI: 10.1145/3351095.3373154

Nathan Kallus, Xiaojie Mao, Angela Zhou

{"title":"Assessing algorithmic fairness with unobserved protected class using data combination","authors":"Nathan Kallus, Xiaojie Mao, Angela Zhou","doi":"10.1145/3351095.3373154","DOIUrl":"https://doi.org/10.1145/3351095.3373154","url":null,"abstract":"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, or performance disparities in general, in practice: protected class membership is often not observed in the data. This is particularly a problem in lending and healthcare. We consider the use of an auxiliary dataset, such as the US census, that includes protected class labels but not decisions or outcomes. We show that a variety of common disparity measures are generally unidentifiable aside for some unrealistic cases, providing a new perspective on the documented biases of popular proxy-based methods. We provide exact characterizations of the sharpest-possible partial identification set of disparities either under no assumptions or when we incorporate mild smoothness constraints. We further provide optimization-based algorithms for computing and visualizing these sets of simultaneously achievable pairwise disparties for assessing disparities that arise between multiple groups, which enables reliable and robust assessments - an important tool when disparity assessment can have far-reaching policy implications. We demonstrate this in two case studies with real data: mortgage lending and personalized medicine dosing.","PeriodicalId":377829,"journal":{"name":"Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117184409","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 113

Fair decision making using privacy-protected data 使用受隐私保护的数据进行公平决策

Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency Pub Date : 2019-05-29 DOI: 10.1145/3351095.3372872

Satya Kuppam, Ryan McKenna, David Pujol, Michael Hay, Ashwin Machanavajjhala, G. Miklau

{"title":"Fair decision making using privacy-protected data","authors":"Satya Kuppam, Ryan McKenna, David Pujol, Michael Hay, Ashwin Machanavajjhala, G. Miklau","doi":"10.1145/3351095.3372872","DOIUrl":"https://doi.org/10.1145/3351095.3372872","url":null,"abstract":"Data collected about individuals is regularly used to make decisions that impact those same individuals. We consider settings where sensitive personal data is used to decide who will receive resources or benefits. While it is well known that there is a trade-off between protecting privacy and the accuracy of decisions, we initiate a first-of-its-kind study into the impact of formally private mechanisms (based on differential privacy) on fair and equitable decision-making. We empirically investigate novel tradeoffs on two real-world decisions made using U.S. Census data (allocation of federal funds and assignment of voting rights benefits) as well as a classic apportionment problem. Our results show that if decisions are made using an ∈-differentially private version of the data, under strict privacy constraints (smaller ∈), the noise added to achieve privacy may disproportionately impact some groups over others. We propose novel measures of fairness in the context of randomized differentially private algorithms and identify a range of causes of outcome disparities. We also explore improved algorithms to remedy the unfairness observed.","PeriodicalId":377829,"journal":{"name":"Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115305415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 69

Explaining machine learning classifiers through diverse counterfactual explanations 通过不同的反事实解释解释机器学习分类器

Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency Pub Date : 2019-05-19 DOI: 10.1145/3351095.3372850

R. Mothilal, Amit Sharma, Chenhao Tan

{"title":"Explaining machine learning classifiers through diverse counterfactual explanations","authors":"R. Mothilal, Amit Sharma, Chenhao Tan","doi":"10.1145/3351095.3372850","DOIUrl":"https://doi.org/10.1145/3351095.3372850","url":null,"abstract":"Post-hoc explanations of machine learning models are crucial for people to understand and act on algorithmic predictions. An intriguing class of explanations is through counterfactuals, hypothetical examples that show people how to obtain a different prediction. We posit that effective counterfactual explanations should satisfy two properties: feasibility of the counterfactual actions given user context and constraints, and diversity among the counterfactuals presented. To this end, we propose a framework for generating and evaluating a diverse set of counterfactual explanations based on determinantal point processes. To evaluate the actionability of counterfactuals, we provide metrics that enable comparison of counterfactual-based methods to other local explanation methods. We further address necessary tradeoffs and point to causal implications in optimizing for counterfactuals. Our experiments on four real-world datasets show that our framework can generate a set of counterfactuals that are diverse and well approximate local decision boundaries, outperforming prior approaches to generating diverse counterfactuals. We provide an implementation of the framework at https://github.com/microsoft/DiCE.","PeriodicalId":377829,"journal":{"name":"Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132712750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 612

Fair classification and social welfare 公平分类和社会福利

Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency Pub Date : 2019-05-01 DOI: 10.1145/3351095.3372857

Lily Hu, Yiling Chen

{"title":"Fair classification and social welfare","authors":"Lily Hu, Yiling Chen","doi":"10.1145/3351095.3372857","DOIUrl":"https://doi.org/10.1145/3351095.3372857","url":null,"abstract":"Now that machine learning algorithms lie at the center of many important resource allocation pipelines, computer scientists have been unwittingly cast as partial social planners. Given this state of affairs, important questions follow. How do leading notions of fairness as defined by computer scientists map onto longer-standing notions of social welfare? In this paper, we present a welfare-based analysis of fair classification regimes. Our main findings assess the welfare impact of fairness-constrained empirical risk minimization programs on the individuals and groups who are subject to their outputs. We fully characterize the ranges of Δ'e perturbations to a fairness parameter 'e in a fair Soft Margin SVM problem that yield better, worse, and neutral outcomes in utility for individuals and by extension, groups. Our method of analysis allows for fast and efficient computation of \"fairness-to-welfare\" solution paths, thereby allowing practitioners to easily assess whether and which fair learning procedures result in classification outcomes that make groups better-off. Our analyses show that applying stricter fairness criteria codified as parity constraints can worsen welfare outcomes for both groups. More generally, always preferring \"more fair\" classifiers does not abide by the Pareto Principle---a fundamental axiom of social choice theory and welfare economics. Recent work in machine learning has rallied around these notions of fairness as critical to ensuring that algorithmic systems do not have disparate negative impact on disadvantaged social groups. By showing that these constraints often fail to translate into improved outcomes for these groups, we cast doubt on their effectiveness as a means to ensure fairness and justice.","PeriodicalId":377829,"journal":{"name":"Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115822726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 73

Preference-informed fairness Preference-informed公平

Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency Pub Date : 2019-04-03 DOI: 10.4230/LIPIcs.ITCS.2020.16

Michael P. Kim, A. Korolova, G. Rothblum, G. Yona

{"title":"Preference-informed fairness","authors":"Michael P. Kim, A. Korolova, G. Rothblum, G. Yona","doi":"10.4230/LIPIcs.ITCS.2020.16","DOIUrl":"https://doi.org/10.4230/LIPIcs.ITCS.2020.16","url":null,"abstract":"In this work, we study notions of fairness in decision-making systems when individuals have diverse preferences over the possible outcomes of the decisions. Our starting point is the seminal work of Dwork et al. [ITCS 2012] which introduced a notion of individual fairness (IF): given a task-specific similarity metric, every pair of individuals who are similarly qualified according to the metric should receive similar outcomes. We show that when individuals have diverse preferences over outcomes, requiring IF may unintentionally lead to less-preferred outcomes for the very individuals that IF aims to protect (e.g. a protected minority group). A natural alternative to IF is the classic notion of fair division, envy-freeness (EF): no individual should prefer another individual's outcome over their own. Although EF allows for solutions where all individuals receive a highly-preferred outcome, EF may also be overly-restrictive for the decision-maker. For instance, if many individuals agree on the best outcome, then if any individual receives this outcome, they all must receive it, regardless of each individual's underlying qualifications for the outcome. We introduce and study a new notion of preference-informed individual fairness (PIIF) that is a relaxation of both individual fairness and envy-freeness. At a high-level, PIIF requires that outcomes satisfy IF-style constraints, but allows for deviations provided they are in line with individuals' preferences. We show that PIIF can permit outcomes that are more favorable to individuals than any IF solution, while providing considerably more flexibility to the decision-maker than EF. In addition, we show how to efficiently optimize any convex objective over the outcomes subject to PIIF for a rich class of individual preferences. Finally, we demonstrate the broad applicability of the PIIF framework by extending our definitions and algorithms to the multiple-task targeted advertising setting introduced by Dwork and Ilvento [ITCS 2019].","PeriodicalId":377829,"journal":{"name":"Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency","volume":"129 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127391303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 25