Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model

Qizhou Wang, Bo Han*, Tongliang Liu, Gang Niu, Jian Yang, Chen Gong*

*Corresponding author for this work

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

13 Citations (Scopus)


The drastic increase of data quantity often brings the severe decrease of data quality, such as incorrect label annotations, which poses a great challenge for robustly training Deep Neural Networks (DNNs). Existing learning methods with label noise either employ ad-hoc heuristics or restrict to specific noise assumptions. However, more general situations, such as instance-dependent label noise, have not been fully explored, as scarce studies focus on their label corruption process. By categorizing instances into confusing and unconfusing instances, this paper proposes a simple yet universal probabilistic model, which explicitly relates noisy labels to their instances. The resultant model can be realized by DNNs, where the training procedure is accomplished by employing an alternating optimization algorithm. Experiments on datasets with both synthetic and real-world label noise verify that the proposed method yields significant improvements on robustness over state-of-the-art counterparts.

Original languageEnglish
Title of host publication35th AAAI Conference on Artificial Intelligence, AAAI 2021
PublisherAssociation for the Advancement of Artificial Intelligence
Number of pages9
ISBN (Electronic)9781713835974
ISBN (Print)9781577358664
Publication statusPublished - 18 May 2021
Event35th AAAI Conference on Artificial Intelligence, AAAI 2021 - Virtual, Online
Duration: 2 Feb 20219 Feb 2021

Publication series

NameProceedings of the AAAI Conference on Artificial Intelligence
ISSN (Print)2159-5399
ISSN (Electronic)2374-3468
NameAAAI-21/ IAAI-21/ EAAI-21 Proceedings


Conference35th AAAI Conference on Artificial Intelligence, AAAI 2021
Internet address

Scopus Subject Areas

  • Artificial Intelligence


Dive into the research topics of 'Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model'. Together they form a unique fingerprint.

Cite this