Towards instance-dependent label noise-tolerant classification: a probabilistic approach

• Main Authors: Jakramate Bootkrajang, Jeerayut Chaijaruwanich
• Format: Journal
• Published: 2018
• Subjects: Computer Science
• Online Access: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85053253900&origin=inward; http://cmuir.cmu.ac.th/jspui/handle/6653943832/62668
• Institution: Chiang Mai University

© 2018, Springer-Verlag London Ltd., part of Springer Nature. Learning from labelled data is becoming more and more challenging due to inherent imperfection of training labels. Existing label noise-tolerant learning machines were primarily designed to tackle class-conditional noise which occurs at random, independently from input instances. However, relatively less attention was given to a more general type of label noise which is influenced by input features. In this paper, we try to address the problem of learning a classifier in the presence of instance-dependent label noise by developing a novel label noise model which is expected to capture the variation of label noise rate within a class. This is accomplished by adopting a probability density function of a mixture of Gaussians to approximate the label flipping probabilities. Experimental results demonstrate the effectiveness of the proposed method over existing approaches.