Formulating data science problems is an uncertain and difficult process. It requires various forms of discretionary work to translate high-level objectives or strategic goals into tractable problems, necessitating, among other things, the identification of appropriate target variables and proxies. While these choices are rarely self-evident, normative assessments of data science projects often take them for granted, even though different translations can raise profoundly different ethical concerns. Whether we consider a data science project fair often has as much to do with the formulation of the problem as any property of the resulting model. Building on six months of ethnographic fieldwork with a corporate data science team---and channeling ideas from sociology and history of science, critical data studies, and early writing on knowledge discovery in databases---we describe the complex set of actors and activities involved in problem formulation. Our research demonstrates that the specification and operationalization of the problem are always negotiated and elastic, and rarely worked out with explicit normative considerations in mind. In so doing, we show that careful accounts of everyday data science work can help us better understand how and why data science problems are posed in certain ways---and why specific formulations prevail in practice, even in the face of what might seem like normatively preferable alternatives. We conclude by discussing the implications of our findings, arguing that effective normative interventions will require attending to the practical work of problem formulation.
{"title":"Problem Formulation and Fairness","authors":"Samir Passi, Solon Barocas","doi":"10.1145/3287560.3287567","DOIUrl":"https://doi.org/10.1145/3287560.3287567","url":null,"abstract":"Formulating data science problems is an uncertain and difficult process. It requires various forms of discretionary work to translate high-level objectives or strategic goals into tractable problems, necessitating, among other things, the identification of appropriate target variables and proxies. While these choices are rarely self-evident, normative assessments of data science projects often take them for granted, even though different translations can raise profoundly different ethical concerns. Whether we consider a data science project fair often has as much to do with the formulation of the problem as any property of the resulting model. Building on six months of ethnographic fieldwork with a corporate data science team---and channeling ideas from sociology and history of science, critical data studies, and early writing on knowledge discovery in databases---we describe the complex set of actors and activities involved in problem formulation. Our research demonstrates that the specification and operationalization of the problem are always negotiated and elastic, and rarely worked out with explicit normative considerations in mind. In so doing, we show that careful accounts of everyday data science work can help us better understand how and why data science problems are posed in certain ways---and why specific formulations prevail in practice, even in the face of what might seem like normatively preferable alternatives. We conclude by discussing the implications of our findings, arguing that effective normative interventions will require attending to the practical work of problem formulation.","PeriodicalId":20573,"journal":{"name":"Proceedings of the Conference on Fairness, Accountability, and Transparency","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75079985","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}
This paper proposes new search algorithms for counterfactual explanations based upon mixed integer programming. We are concerned with complex data in which variables may take any value from a contiguous range or an additional set of discrete states. We propose a novel set of constraints that we refer to as a "mixed polytope" and show how this can be used with an integer programming solver to efficiently find coherent counterfactual explanations i.e. solutions that are guaranteed to map back onto the underlying data structure, while avoiding the need for brute-force enumeration. We also look at the problem of diverse explanations and show how these can be generated within our framework.
{"title":"Efficient Search for Diverse Coherent Explanations","authors":"Chris Russell","doi":"10.1145/3287560.3287569","DOIUrl":"https://doi.org/10.1145/3287560.3287569","url":null,"abstract":"This paper proposes new search algorithms for counterfactual explanations based upon mixed integer programming. We are concerned with complex data in which variables may take any value from a contiguous range or an additional set of discrete states. We propose a novel set of constraints that we refer to as a \"mixed polytope\" and show how this can be used with an integer programming solver to efficiently find coherent counterfactual explanations i.e. solutions that are guaranteed to map back onto the underlying data structure, while avoiding the need for brute-force enumeration. We also look at the problem of diverse explanations and show how these can be generated within our framework.","PeriodicalId":20573,"journal":{"name":"Proceedings of the Conference on Fairness, Accountability, and Transparency","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82588574","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}
{"title":"Proceedings of the Conference on Fairness, Accountability, and Transparency","authors":"","doi":"10.1145/3287560","DOIUrl":"https://doi.org/10.1145/3287560","url":null,"abstract":"","PeriodicalId":20573,"journal":{"name":"Proceedings of the Conference on Fairness, Accountability, and Transparency","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72684473","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}
Hussein Mozannar, Mesrob I. Ohannessian, N. Srebro
The study of fairness in intelligent decision systems has mostly ignored long-term influence on the underlying population. Yet fairness considerations (e.g. affirmative action) have often the implicit goal of achieving balance among groups within the population. The most basic notion of balance is eventual equality between the qualifications of the groups. How can we incorporate influence dynamics in decision making? How well do dynamics-oblivious fairness policies fare in terms of reaching equality? In this paper, we propose a simple yet revealing model that encompasses (1) a selection process where an institution chooses from multiple groups according to their qualifications so as to maximize an institutional utility and (2) dynamics that govern the evolution of the groups' qualifications according to the imposed policies. We focus on demographic parity as the formalism of affirmative action. We first give conditions under which an unconstrained policy reaches equality on its own. In this case, surprisingly, imposing demographic parity may break equality. When it doesn't, one would expect the additional constraint to reduce utility, however, we show that utility may in fact increase. In real world scenarios, unconstrained policies do not lead to equality. In such cases, we show that although imposing demographic parity may remedy it, there is a danger that groups settle at a worse set of qualifications. As a silver lining, we also identify when the constraint not only leads to equality, but also improves all groups. These cases and trade-offs are instrumental in determining when and how imposing demographic parity can be beneficial in selection processes, both for the institution and for society on the long run.
{"title":"From Fair Decision Making To Social Equality","authors":"Hussein Mozannar, Mesrob I. Ohannessian, N. Srebro","doi":"10.1145/3287560.3287599","DOIUrl":"https://doi.org/10.1145/3287560.3287599","url":null,"abstract":"The study of fairness in intelligent decision systems has mostly ignored long-term influence on the underlying population. Yet fairness considerations (e.g. affirmative action) have often the implicit goal of achieving balance among groups within the population. The most basic notion of balance is eventual equality between the qualifications of the groups. How can we incorporate influence dynamics in decision making? How well do dynamics-oblivious fairness policies fare in terms of reaching equality? In this paper, we propose a simple yet revealing model that encompasses (1) a selection process where an institution chooses from multiple groups according to their qualifications so as to maximize an institutional utility and (2) dynamics that govern the evolution of the groups' qualifications according to the imposed policies. We focus on demographic parity as the formalism of affirmative action. We first give conditions under which an unconstrained policy reaches equality on its own. In this case, surprisingly, imposing demographic parity may break equality. When it doesn't, one would expect the additional constraint to reduce utility, however, we show that utility may in fact increase. In real world scenarios, unconstrained policies do not lead to equality. In such cases, we show that although imposing demographic parity may remedy it, there is a danger that groups settle at a worse set of qualifications. As a silver lining, we also identify when the constraint not only leads to equality, but also improves all groups. These cases and trade-offs are instrumental in determining when and how imposing demographic parity can be beneficial in selection processes, both for the institution and for society on the long run.","PeriodicalId":20573,"journal":{"name":"Proceedings of the Conference on Fairness, Accountability, and Transparency","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87176836","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}
Controversies around race and machine learning have sparked debate among computer scientists over how to design machine learning systems that guarantee fairness. These debates rarely engage with how racial identity is embedded in our social experience, making for sociological and psychological complexity. This complexity challenges the paradigm of considering fairness to be a formal property of supervised learning with respect to protected personal attributes. Racial identity is not simply a personal subjective quality. For people labeled "Black" it is an ascribed political category that has consequences for social differentiation embedded in systemic patterns of social inequality achieved through both social and spatial segregation. In the United States, racial classification can best be understood as a system of inherently unequal status categories that places whites as the most privileged category while signifying the Negro/black category as stigmatized. Social stigma is reinforced through the unequal distribution of societal rewards and goods along racial lines that is reinforced by state, corporate, and civic institutions and practices. This creates a dilemma for society and designers: be blind to racial group disparities and thereby reify racialized social inequality by no longer measuring systemic inequality, or be conscious of racial categories in a way that itself reifies race. We propose a third option. By preceding group fairness interventions with unsupervised learning to dynamically detect patterns of segregation, machine learning systems can mitigate the root cause of social disparities, social segregation and stratification, without further anchoring status categories of disadvantage.
{"title":"Racial categories in machine learning","authors":"Sebastian Benthall, Bruce D. Haynes","doi":"10.1145/3287560.3287575","DOIUrl":"https://doi.org/10.1145/3287560.3287575","url":null,"abstract":"Controversies around race and machine learning have sparked debate among computer scientists over how to design machine learning systems that guarantee fairness. These debates rarely engage with how racial identity is embedded in our social experience, making for sociological and psychological complexity. This complexity challenges the paradigm of considering fairness to be a formal property of supervised learning with respect to protected personal attributes. Racial identity is not simply a personal subjective quality. For people labeled \"Black\" it is an ascribed political category that has consequences for social differentiation embedded in systemic patterns of social inequality achieved through both social and spatial segregation. In the United States, racial classification can best be understood as a system of inherently unequal status categories that places whites as the most privileged category while signifying the Negro/black category as stigmatized. Social stigma is reinforced through the unequal distribution of societal rewards and goods along racial lines that is reinforced by state, corporate, and civic institutions and practices. This creates a dilemma for society and designers: be blind to racial group disparities and thereby reify racialized social inequality by no longer measuring systemic inequality, or be conscious of racial categories in a way that itself reifies race. We propose a third option. By preceding group fairness interventions with unsupervised learning to dynamically detect patterns of segregation, machine learning systems can mitigate the root cause of social disparities, social segregation and stratification, without further anchoring status categories of disadvantage.","PeriodicalId":20573,"journal":{"name":"Proceedings of the Conference on Fairness, Accountability, and Transparency","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89860551","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}
Jiahao Chen, Nathan Kallus, Xiaojie Mao, G. Svacha, Madeleine Udell
Assessing the fairness of a decision making system with respect to a protected class, such as gender or race, is challenging when class membership labels are unavailable. Probabilistic models for predicting the protected class based on observable proxies, such as surname and geolocation for race, are sometimes used to impute these missing labels for compliance assessments. Empirically, these methods are observed to exaggerate disparities, but the reason why is unknown. In this paper, we decompose the biases in estimating outcome disparity via threshold-based imputation into multiple interpretable bias sources, allowing us to explain when over- or underestimation occurs. We also propose an alternative weighted estimator that uses soft classification, and show that its bias arises simply from the conditional covariance of the outcome with the true class membership. Finally, we illustrate our results with numerical simulations and a public dataset of mortgage applications, using geolocation as a proxy for race. We confirm that the bias of threshold-based imputation is generally upward, but its magnitude varies strongly with the threshold chosen. Our new weighted estimator tends to have a negative bias that is much simpler to analyze and reason about.
{"title":"Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobserved","authors":"Jiahao Chen, Nathan Kallus, Xiaojie Mao, G. Svacha, Madeleine Udell","doi":"10.1145/3287560.3287594","DOIUrl":"https://doi.org/10.1145/3287560.3287594","url":null,"abstract":"Assessing the fairness of a decision making system with respect to a protected class, such as gender or race, is challenging when class membership labels are unavailable. Probabilistic models for predicting the protected class based on observable proxies, such as surname and geolocation for race, are sometimes used to impute these missing labels for compliance assessments. Empirically, these methods are observed to exaggerate disparities, but the reason why is unknown. In this paper, we decompose the biases in estimating outcome disparity via threshold-based imputation into multiple interpretable bias sources, allowing us to explain when over- or underestimation occurs. We also propose an alternative weighted estimator that uses soft classification, and show that its bias arises simply from the conditional covariance of the outcome with the true class membership. Finally, we illustrate our results with numerical simulations and a public dataset of mortgage applications, using geolocation as a proxy for race. We confirm that the bias of threshold-based imputation is generally upward, but its magnitude varies strongly with the threshold chosen. Our new weighted estimator tends to have a negative bias that is much simpler to analyze and reason about.","PeriodicalId":20573,"journal":{"name":"Proceedings of the Conference on Fairness, Accountability, and Transparency","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73797294","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}
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 cases, insights into what fairness means and how to measure it have largely gone overlooked. We compare past and current notions of fairness along several dimensions, including the fairness criteria, the focus of the criteria (e.g., a test, a model, or its use), the relationship of fairness to individuals, groups, and subgroups, and the mathematical method for measuring fairness (e.g., classification, regression). This work points the way towards future research and measurement of (un)fairness that builds from our modern understanding of fairness while incorporating insights from the past.
{"title":"50 Years of Test (Un)fairness: Lessons for Machine Learning","authors":"B. Hutchinson, Margaret Mitchell","doi":"10.1145/3287560.3287600","DOIUrl":"https://doi.org/10.1145/3287560.3287600","url":null,"abstract":"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 cases, insights into what fairness means and how to measure it have largely gone overlooked. We compare past and current notions of fairness along several dimensions, including the fairness criteria, the focus of the criteria (e.g., a test, a model, or its use), the relationship of fairness to individuals, groups, and subgroups, and the mathematical method for measuring fairness (e.g., classification, regression). This work points the way towards future research and measurement of (un)fairness that builds from our modern understanding of fairness while incorporating insights from the past.","PeriodicalId":20573,"journal":{"name":"Proceedings of the Conference on Fairness, Accountability, and Transparency","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88391349","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}
Abhijnan Chakraborty, Gourab K. Patro, Niloy Ganguly, K. Gummadi, P. Loiseau
To help their users to discover important items at a particular time, major websites like Twitter, Yelp, TripAdvisor or NYTimes provide Top-K recommendations (e.g., 10 Trending Topics, Top 5 Hotels in Paris or 10 Most Viewed News Stories), which rely on crowdsourced popularity signals to select the items. However, different sections of a crowd may have different preferences, and there is a large silent majority who do not explicitly express their opinion. Also, the crowd often consists of actors like bots, spammers, or people running orchestrated campaigns. Recommendation algorithms today largely do not consider such nuances, hence are vulnerable to strategic manipulation by small but hyper-active user groups. To fairly aggregate the preferences of all users while recommending top-K items, we borrow ideas from prior research on social choice theory, and identify a voting mechanism called Single Transferable Vote (STV) as having many of the fairness properties we desire in top-K item (s)elections. We develop an innovative mechanism to attribute preferences of silent majority which also make STV completely operational. We show the generalizability of our approach by implementing it on two different real-world datasets. Through extensive experimentation and comparison with state-of-the-art techniques, we show that our proposed approach provides maximum user satisfaction, and cuts down drastically on items disliked by most but hyper-actively promoted by a few users.
{"title":"Equality of Voice: Towards Fair Representation in Crowdsourced Top-K Recommendations","authors":"Abhijnan Chakraborty, Gourab K. Patro, Niloy Ganguly, K. Gummadi, P. Loiseau","doi":"10.1145/3287560.3287570","DOIUrl":"https://doi.org/10.1145/3287560.3287570","url":null,"abstract":"To help their users to discover important items at a particular time, major websites like Twitter, Yelp, TripAdvisor or NYTimes provide Top-K recommendations (e.g., 10 Trending Topics, Top 5 Hotels in Paris or 10 Most Viewed News Stories), which rely on crowdsourced popularity signals to select the items. However, different sections of a crowd may have different preferences, and there is a large silent majority who do not explicitly express their opinion. Also, the crowd often consists of actors like bots, spammers, or people running orchestrated campaigns. Recommendation algorithms today largely do not consider such nuances, hence are vulnerable to strategic manipulation by small but hyper-active user groups. To fairly aggregate the preferences of all users while recommending top-K items, we borrow ideas from prior research on social choice theory, and identify a voting mechanism called Single Transferable Vote (STV) as having many of the fairness properties we desire in top-K item (s)elections. We develop an innovative mechanism to attribute preferences of silent majority which also make STV completely operational. We show the generalizability of our approach by implementing it on two different real-world datasets. Through extensive experimentation and comparison with state-of-the-art techniques, we show that our proposed approach provides maximum user satisfaction, and cuts down drastically on items disliked by most but hyper-actively promoted by a few users.","PeriodicalId":20573,"journal":{"name":"Proceedings of the Conference on Fairness, Accountability, and Transparency","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85705867","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}
Humans are the final decision makers in critical tasks that involve ethical and legal concerns, ranging from recidivism prediction, to medical diagnosis, to fighting against fake news. Although machine learning models can sometimes achieve impressive performance in these tasks, these tasks are not amenable to full automation. To realize the potential of machine learning for improving human decisions, it is important to understand how assistance from machine learning models affects human performance and human agency. In this paper, we use deception detection as a testbed and investigate how we can harness explanations and predictions of machine learning models to improve human performance while retaining human agency. We propose a spectrum between full human agency and full automation, and develop varying levels of machine assistance along the spectrum that gradually increase the influence of machine predictions. We find that without showing predicted labels, explanations alone slightly improve human performance in the end task. In comparison, human performance is greatly improved by showing predicted labels (>20% relative improvement) and can be further improved by explicitly suggesting strong machine performance. Interestingly, when predicted labels are shown, explanations of machine predictions induce a similar level of accuracy as an explicit statement of strong machine performance. Our results demonstrate a tradeoff between human performance and human agency and show that explanations of machine predictions can moderate this tradeoff.
{"title":"On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection","authors":"Vivian Lai, Chenhao Tan","doi":"10.1145/3287560.3287590","DOIUrl":"https://doi.org/10.1145/3287560.3287590","url":null,"abstract":"Humans are the final decision makers in critical tasks that involve ethical and legal concerns, ranging from recidivism prediction, to medical diagnosis, to fighting against fake news. Although machine learning models can sometimes achieve impressive performance in these tasks, these tasks are not amenable to full automation. To realize the potential of machine learning for improving human decisions, it is important to understand how assistance from machine learning models affects human performance and human agency. In this paper, we use deception detection as a testbed and investigate how we can harness explanations and predictions of machine learning models to improve human performance while retaining human agency. We propose a spectrum between full human agency and full automation, and develop varying levels of machine assistance along the spectrum that gradually increase the influence of machine predictions. We find that without showing predicted labels, explanations alone slightly improve human performance in the end task. In comparison, human performance is greatly improved by showing predicted labels (>20% relative improvement) and can be further improved by explicitly suggesting strong machine performance. Interestingly, when predicted labels are shown, explanations of machine predictions induce a similar level of accuracy as an explicit statement of strong machine performance. Our results demonstrate a tradeoff between human performance and human agency and show that explanations of machine predictions can moderate this tradeoff.","PeriodicalId":20573,"journal":{"name":"Proceedings of the Conference on Fairness, Accountability, and Transparency","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85823061","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}
Recent advances in deep learning have achieved impressive gains in classification accuracy on a variety of types of data, including images and text. Despite these gains, however, concerns have been raised about the calibration, robustness, and interpretability of these models. In this paper we propose a simple way to modify any conventional deep architecture to automatically provide more transparent explanations for classification decisions, as well as an intuitive notion of the credibility of each prediction. Specifically, we draw on ideas from nonparametric kernel regression, and propose to predict labels based on a weighted sum of training instances, where the weights are determined by distance in a learned instance-embedding space. Working within the framework of conformal methods, we propose a new measure of nonconformity suggested by our model, and experimentally validate the accompanying theoretical expectations, demonstrating improved transparency, controlled error rates, and robustness to out-of-domain data, without compromising on accuracy or calibration.
{"title":"Deep Weighted Averaging Classifiers","authors":"Dallas Card, Michael J.Q. Zhang, Noah A. Smith","doi":"10.1145/3287560.3287595","DOIUrl":"https://doi.org/10.1145/3287560.3287595","url":null,"abstract":"Recent advances in deep learning have achieved impressive gains in classification accuracy on a variety of types of data, including images and text. Despite these gains, however, concerns have been raised about the calibration, robustness, and interpretability of these models. In this paper we propose a simple way to modify any conventional deep architecture to automatically provide more transparent explanations for classification decisions, as well as an intuitive notion of the credibility of each prediction. Specifically, we draw on ideas from nonparametric kernel regression, and propose to predict labels based on a weighted sum of training instances, where the weights are determined by distance in a learned instance-embedding space. Working within the framework of conformal methods, we propose a new measure of nonconformity suggested by our model, and experimentally validate the accompanying theoretical expectations, demonstrating improved transparency, controlled error rates, and robustness to out-of-domain data, without compromising on accuracy or calibration.","PeriodicalId":20573,"journal":{"name":"Proceedings of the Conference on Fairness, Accountability, and Transparency","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82451712","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：