Which is Better for Learning with Noisy Labels: The Semi-supervised Method or Modeling Label Noise?

Yu Yao, Mingming Gong, Yuxuan Du, Jun Yu, Bo Han, Kun Zhang, Tongliang Liu*

*Corresponding author for this work

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

Abstract

In real life, accurately annotating large-scale datasets is sometimes difficult. Datasets used for training deep learning models are likely to contain label noise. To make use of the dataset containing label noise, two typical methods have been proposed. One is to employ the semi-supervised method by exploiting labeled confident examples and unlabeled unconfident examples. The other one is to model label noise and design statistically consistent classifiers. A natural question remains unsolved: which one should be used for a specific real-world application? In this paper, we answer the question from the perspective of causal data generative process. Specifically, the performance of the semi-supervised based method depends heavily on the data generative process while the method modeling label-noise is not influenced by the generation process. For example, for a given dataset, if it has a causal generative structure that the features cause the label, the semi-supervised based method would not be helpful. When the causal structure is unknown, we provide an intuitive method to discover the causal structure for a given dataset containing label noise.

Original languageEnglish
Title of host publicationProceedings of 40th International Conference on Machine Learning, ICML 2023
EditorsAndreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, Jonathan Scarlett
PublisherML Research Press
Pages39660-39673
Number of pages14
Publication statusPublished - Jul 2023
Event40th International Conference on Machine Learning, ICML 2023 - Honolulu, United States
Duration: 23 Jul 202329 Jul 2023
https://icml.cc/Conferences/2023
https://proceedings.mlr.press/v202/
https://openreview.net/group?id=ICML.cc/2023/Conference

Publication series

NameProceedings of Machine Learning Research
PublisherML Research Press
Volume202
ISSN (Print)2640-3498

Conference

Conference40th International Conference on Machine Learning, ICML 2023
Country/TerritoryUnited States
CityHonolulu
Period23/07/2329/07/23
Internet address

Scopus Subject Areas

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

Fingerprint

Dive into the research topics of 'Which is Better for Learning with Noisy Labels: The Semi-supervised Method or Modeling Label Noise?'. Together they form a unique fingerprint.

Cite this