Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning

Yu Yao, Tongliang Liu*, Bo Han, Mingming Gong, Jiankang Deng, Gang Niu, Masashi Sugiyama

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference contributionpeer-review

20 Citations (Scopus)

Abstract

The transition matrix, denoting the transition relationship from clean labels to noisy labels, is essential to build statistically consistent classifiers in label-noise learning. Existing methods for estimating the transition matrix rely heavily on estimating the noisy class posterior. However, the estimation error for noisy class posterior could be large because of the randomness of label noise. The estimation error would lead the transition matrix to be poorly estimated. Therefore in this paper, we aim to solve this problem by exploiting the divide-and-conquer paradigm. Specifically, we introduce an intermediate class to avoid directly estimating the noisy class posterior. By this intermediate class, the original transition matrix can then be factorized into the product of two easy-to-estimated transition matrices. We term the proposed method as the dual T-estimator. Both theoretical analyses and empirical results illustrate the effectiveness of the dual T-estimator for estimating transition matrices, leading to better classification performances.
Original languageEnglish
Title of host publication34th Conference on Neural Information Processing Systems (NeurIPS 2020)
EditorsH. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, H. Lin
PublisherNeural Information Processing Systems Foundation
Pages7260-7271
Number of pages12
Volume9
ISBN (Print)9781713829546
DOIs
Publication statusPublished - 6 Dec 2020
Event34th Conference on Neural Information Processing Systems, NeurIPS 2020 - Virtual, Online
Duration: 6 Dec 202012 Dec 2020

Publication series

NameAdvances in Neural Information Processing Systems
Volume33
ISSN (Print)1049-5258
NameNeurIPS Proceedings

Conference

Conference34th Conference on Neural Information Processing Systems, NeurIPS 2020
CityVirtual, Online
Period6/12/2012/12/20

Scopus Subject Areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint

Dive into the research topics of 'Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning'. Together they form a unique fingerprint.

Cite this