Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels

Songhua Wu, Xiaobo Xia, Tongliang Liu*, Bo Han, Mingming Gong, Nannan Wang, Haifeng Liu, Gang Niu

*Corresponding author for this work

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

40 Citations (Scopus)

Abstract

Learning with noisy labels has attracted a lot of attention in recent years, where the mainstream approaches are in pointwise manners. Meanwhile, pairwise manners have shown great potential in supervised metric learning and unsupervised contrastive learning. Thus, a natural question is raised: does learning in a pairwise manner mitigate label noise? To give an affirmative answer, in this paper, we propose a framework called Class2Simi: it transforms data points with noisy class labels to data pairs with noisy similarity labels, where a similarity label denotes whether a pair shares the class label or not. Through this transformation, the reduction of the noise rate is theoretically guaranteed, and hence it is in principle easier to handle noisy similarity labels. Amazingly, DNNs that predict the clean class labels can be trained from noisy data pairs if they are first pretrained from noisy data points. Class2Simi is computationally efficient because not only this transformation is on-the-fly in mini-batches, but also it just changes loss computation on top of model prediction into a pairwise manner. Its effectiveness is verified by extensive experiments.

Original languageEnglish
Title of host publicationProceedings of the 38th International Conference on Machine Learning, ICML 2021
PublisherMathematical Research Press
Pages11285-11295
Number of pages11
ISBN (Electronic)9781713845065
Publication statusPublished - 18 Jul 2021
Event38th International Conference on Machine Learning, ICML 2021 - Virtual, Online
Duration: 18 Jul 202124 Jul 2021

Publication series

NameProceedings of Machine Learning Research
Volume139
ISSN (Electronic)2640-3498

Conference

Conference38th International Conference on Machine Learning, ICML 2021
CityVirtual, Online
Period18/07/2124/07/21

Scopus Subject Areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels'. Together they form a unique fingerprint.

Cite this