Instance-dependent Label-noise Learning under a Structural Causal Model

Yu Yao, Tongliang Liu*, Mingming Gong, Bo Han, Gang Niu, Kun Zhang

*Corresponding author for this work

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

20 Citations (Scopus)


Label noise generally degenerates the performance of deep learning algorithms because deep neural networks easily overfit label errors. Let X and Y denote the instance and clean label, respectively. When Y is a cause of X, according to which many datasets have been constructed, e.g., SVHN and CIFAR, the distributions of P(X) and P(Y |X) are generally entangled. This means that the unsupervised instances are helpful to learn the classifier and thus reduce the side effect of label noise. However, it remains elusive on how to exploit the causal information to handle the label-noise problem. We propose to model and make use of the causal process in order to correct the label-noise effect. Empirically, the proposed method outperforms all state-of-the-art methods on both synthetic and real-world label-noise datasets.

Original languageEnglish
Title of host publication35th Conference on Neural Information Processing Systems (NeurIPS 2021)
EditorsMarc'Aurelio Ranzato, Alina Beygelzimer, Yann Dauphin, Percy S. Liang, Jenn Wortman Vaughan
PublisherNeural Information Processing Systems Foundation
Number of pages12
ISBN (Print)9781713845393
Publication statusPublished - 6 Dec 2021
Event35th Conference on Neural Information Processing Systems, NeurIPS 2021 - Virtual, Online
Duration: 6 Dec 202114 Dec 2021

Publication series

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


Conference35th Conference on Neural Information Processing Systems, NeurIPS 2021
Internet address

Scopus Subject Areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing


Dive into the research topics of 'Instance-dependent Label-noise Learning under a Structural Causal Model'. Together they form a unique fingerprint.

Cite this