Privacy-Preserving Cost-Sensitive Learning

Yang，Yi1; Huang，Shuai2; Huang，Wei3,4; Chang，Xiangyu1

2021-05-01

10.1109/TNNLS.2020.2996972

IEEE Transactions on Neural Networks and Learning Systems   影响因子和分区

2162-237X

2162-2388

Cost-sensitive learning methods guaranteeing privacy are becoming crucial nowadays in many applications where increasing use of sensitive personal information is observed. However, there has no optimal learning scheme developed in the literature to learn cost-sensitive classifiers under constraint of enforcing differential privacy. Our approach is to first develop a unified framework for existing cost-sensitive learning methods by incorporating the weight constant and weight functions into the classical regularized empirical risk minimization framework. Then, we propose two privacy-preserving algorithms with output perturbation and objective perturbation methods, respectively, to be integrated with the cost-sensitive learning framework. We showcase how this general framework can be used analytically by deriving the privacy-preserving cost-sensitive extensions of logistic regression and support vector machine. Experimental evidence on both synthetic and real data sets verifies that the proposed algorithms can reduce the misclassification cost effectively while satisfying the privacy requirement. A theoretical investigation is also conducted, revealing a very interesting analytic relation, i.e., that the choice of the weight constant and weight functions does not only influence the Fisher-consistent property (population minimizer of expected risk with a specific loss function leads to the Bayes optimal decision rule) but also interacts with privacy-preserving levels to affect the performance of classifiers significantly.

Cost-sensitive learning differential privacy Fisher consistency privacy data

SCI ; EI

英语

其他

WOS:000647397200024

20212010351719

Learning systems ; Logistic regression ; Perturbation techniques ; Support vector machines ; Support vector regression

Computer Software, Data Handling and Applications:723 ; Mathematics:921

2-s2.0-85105574608

Scopus

1.Center of Intelligent Decision-Making and Machine Learning,School of Management,Xi'an Jiaotong University,Xi'an,710049,China
2.Department of Industrial and Systems Engineering,University of Washington,Seattle,98195,United States
3.College of Business,South University of Science and Technology,Shenzhen,518055,China
4.School of Management,Xi'an Jiaotong University,Xi'an,710049,China

Yang，Yi,Huang，Shuai,Huang，Wei,et al. Privacy-Preserving Cost-Sensitive Learning[J]. IEEE Transactions on Neural Networks and Learning Systems,2021,32(5):2105-2116.

Yang，Yi,Huang，Shuai,Huang，Wei,&Chang，Xiangyu.(2021).Privacy-Preserving Cost-Sensitive Learning.IEEE Transactions on Neural Networks and Learning Systems,32(5),2105-2116.

Yang，Yi,et al."Privacy-Preserving Cost-Sensitive Learning".IEEE Transactions on Neural Networks and Learning Systems 32.5(2021):2105-2116.