Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society最新文献_第9页

Crowdsourcing with Fairness, Diversity and Budget Constraints 公平、多样性和预算约束下的众包

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society Pub Date : 2018-10-31 DOI: 10.1145/3306618.3314282

Naman Goel, B. Faltings

引用次数: 16

Taking Advantage of Multitask Learning for Fair Classification 利用多任务学习实现公平分类

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society Pub Date : 2018-10-19 DOI: 10.1145/3306618.3314255

L. Oneto, Michele Donini, Amon Elders, M. Pontil

{"title":"Taking Advantage of Multitask Learning for Fair Classification","authors":"L. Oneto, Michele Donini, Amon Elders, M. Pontil","doi":"10.1145/3306618.3314255","DOIUrl":"https://doi.org/10.1145/3306618.3314255","url":null,"abstract":"A central goal of algorithmic fairness is to reduce bias in automated decision making. An unavoidable tension exists between accuracy gains obtained by using sensitive information as part of a statistical model, and any commitment to protect these characteristics. Often, due to biases present in the data, using the sensitive information in the functional form of a classifier improves classification accuracy. In this paper we show how it is possible to get the best of both worlds: optimize model accuracy and fairness without explicitly using the sensitive feature in the functional form of the model, thereby treating different individuals equally. Our method is based on two key ideas. On the one hand, we propose to use Multitask Learning (MTL), enhanced with fairness constraints, to jointly learn group specific classifiers that leverage information between sensitive groups. On the other hand, since learning group specific models might not be permitted, we propose to first predict the sensitive features by any learning method and then to use the predicted sensitive feature to train MTL with fairness constraints. This enables us to tackle fairness with a three-pronged approach, that is, by increasing accuracy on each group, enforcing measures of fairness during training, and protecting sensitive information during testing. Experimental results on two real datasets support our proposal, showing substantial improvements in both accuracy and fairness.","PeriodicalId":418125,"journal":{"name":"Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126891379","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: 53

Active Fairness in Algorithmic Decision Making 算法决策中的主动公平性

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society Pub Date : 2018-09-28 DOI: 10.1145/3306618.3314277

Alejandro Noriega-Campero, Michiel A. Bakker, Bernardo Garcia-Bulle, A. Pentland

{"title":"Active Fairness in Algorithmic Decision Making","authors":"Alejandro Noriega-Campero, Michiel A. Bakker, Bernardo Garcia-Bulle, A. Pentland","doi":"10.1145/3306618.3314277","DOIUrl":"https://doi.org/10.1145/3306618.3314277","url":null,"abstract":"Society increasingly relies on machine learning models for automated decision making. Yet, efficiency gains from automation have come paired with concern for algorithmic discrimination that can systematize inequality. Recent work has proposed optimal post-processing methods that randomize classification decisions for a fraction of individuals, in order to achieve fairness measures related to parity in errors and calibration. These methods, however, have raised concern due to the information inefficiency, intra-group unfairness, and Pareto sub-optimality they entail. The present work proposes an alternativeactive framework for fair classification, where, in deployment, a decision-maker adaptively acquires information according to the needs of different groups or individuals, towards balancing disparities in classification performance. We propose two such methods, where information collection is adapted to group- and individual-level needs respectively. We show on real-world datasets that these can achieve: 1) calibration and single error parity (e.g.,equal opportunity ); and 2) parity in both false positive and false negative rates (i.e.,equal odds ). Moreover, we show that by leveraging their additional degree of freedom,active approaches can substantially outperform randomization-based classifiers previously considered optimal, while avoiding limitations such as intra-group unfairness.","PeriodicalId":418125,"journal":{"name":"Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125173618","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: 70

Counterfactual Fairness in Text Classification through Robustness 基于鲁棒性的文本分类中的反事实公平性

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society Pub Date : 2018-09-27 DOI: 10.1145/3306618.3317950

Sahaj Garg, Vincent Perot, Nicole Limtiaco, Ankur Taly, Ed H. Chi, Alex Beutel

引用次数: 209

Creating Fair Models of Atherosclerotic Cardiovascular Disease Risk 建立公平的动脉粥样硬化性心血管疾病风险模型

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society Pub Date : 2018-09-12 DOI: 10.1145/3306618.3314278

S. Pfohl, Ben J. Marafino, Adrien Coulet, F. Rodriguez, L. Palaniappan, N. Shah

引用次数: 56

Learning Existing Social Conventions via Observationally Augmented Self-Play 通过观察增强自我游戏学习现有社会习俗

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society Pub Date : 2018-06-26 DOI: 10.1145/3306618.3314268

Adam Lerer, A. Peysakhovich

{"title":"Learning Existing Social Conventions via Observationally Augmented Self-Play","authors":"Adam Lerer, A. Peysakhovich","doi":"10.1145/3306618.3314268","DOIUrl":"https://doi.org/10.1145/3306618.3314268","url":null,"abstract":"In order for artificial agents to coordinate effectively with people, they must act consistently with existing conventions (e.g. how to navigate in traffic, which language to speak, or how to coordinate with teammates). A group's conventions can be viewed as a choice of equilibrium in a coordination game. We consider the problem of an agent learning a policy for a coordination game in a simulated environment and then using this policy when it enters an existing group. When there are multiple possible conventions we show that learning a policy via multi-agent reinforcement learning (MARL) is likely to find policies which achieve high payoffs at training time but fail to coordinate with the real group into which the agent enters. We assume access to a small number of samples of behavior from the true convention and show that we can augment the MARL objective to help it find policies consistent with the real group's convention. In three environments from the literature - traffic, communication, and team coordination - we observe that augmenting MARL with a small amount of imitation learning greatly increases the probability that the strategy found by MARL fits well with the existing social convention. We show that this works even in an environment where standard training methods very rarely find the true convention of the agent's partners.","PeriodicalId":418125,"journal":{"name":"Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society","volume":"360 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123129813","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: 45

Multiaccuracy: Black-Box Post-Processing for Fairness in Classification 多精度:分类公平性的黑箱后处理

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society Pub Date : 2018-05-31 DOI: 10.1145/3306618.3314287

Michael P. Kim, Amirata Ghorbani, James Y. Zou

{"title":"Multiaccuracy: Black-Box Post-Processing for Fairness in Classification","authors":"Michael P. Kim, Amirata Ghorbani, James Y. Zou","doi":"10.1145/3306618.3314287","DOIUrl":"https://doi.org/10.1145/3306618.3314287","url":null,"abstract":"Prediction systems are successfully deployed in applications ranging from disease diagnosis, to predicting credit worthiness, to image recognition. Even when the overall accuracy is high, these systems may exhibit systematic biases that harm specific subpopulations; such biases may arise inadvertently due to underrepresentation in the data used to train a machine-learning model, or as the result of intentional malicious discrimination. We develop a rigorous framework of *multiaccuracy* auditing and post-processing to ensure accurate predictions across *identifiable subgroups*. Our algorithm, MULTIACCURACY-BOOST, works in any setting where we have black-box access to a predictor and a relatively small set of labeled data for auditing; importantly, this black-box framework allows for improved fairness and accountability of predictions, even when the predictor is minimally transparent. We prove that MULTIACCURACY-BOOST converges efficiently and show that if the initial model is accurate on an identifiable subgroup, then the post-processed model will be also. We experimentally demonstrate the effectiveness of the approach to improve the accuracy among minority subgroups in diverse applications (image classification, finance, population health). Interestingly, MULTIACCURACY-BOOST can improve subpopulation accuracy (e.g. for \"black women\") even when the sensitive features (e.g. \"race\", \"gender\") are not given to the algorithm explicitly.","PeriodicalId":418125,"journal":{"name":"Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123807587","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: 240

Incomplete Contracting and AI Alignment 不完全契约和AI对齐

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society Pub Date : 2018-04-12 DOI: 10.1145/3306618.3314250

Dylan Hadfield-Menell, Gillian K. Hadfield

{"title":"Incomplete Contracting and AI Alignment","authors":"Dylan Hadfield-Menell, Gillian K. Hadfield","doi":"10.1145/3306618.3314250","DOIUrl":"https://doi.org/10.1145/3306618.3314250","url":null,"abstract":"We suggest that the analysis of incomplete contracting developed by law and economics researchers can provide a useful framework for understanding the AI alignment problem and help to generate a systematic approach to finding solutions. We first provide an overview of the incomplete contracting literature and explore parallels between this work and the problem of AI alignment. As we emphasize, misalignment between principal and agent is a core focus of economic analysis. We highlight some technical results from the economics literature on incomplete contracts that may provide insights for AI alignment researchers. Our core contribution, however, is to bring to bear an insight that economists have been urged to absorb from legal scholars and other behavioral scientists: the fact that human contracting is supported by substantial amounts of external structure, such as generally available institutions (culture, law) that can supply implied terms to fill the gaps in incomplete contracts. We propose a research agenda for AI alignment work that focuses on the problem of how to build AI that can replicate the human cognitive processes that connect individual incomplete contracts with this supporting external structure.","PeriodicalId":418125,"journal":{"name":"Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130747480","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: 44

Paradoxes in Fair Computer-Aided Decision Making 公平计算机辅助决策中的悖论

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society Pub Date : 2017-11-29 DOI: 10.1145/3306618.3314242

Andrew Morgan, R. Pass

引用次数: 8

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society 2019年AAAI/ACM人工智能、伦理与社会会议论文集

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society Pub Date : 1900-01-01 DOI: 10.1145/3306618

引用次数: 11