Candidate-Label Learning: A Generalization of Ordinary-Label Learning and Complementary-Label Learning

Yasuhiro Katsura*, Masato Uchida

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


A supervised learning framework has been proposed for a situation in which each training data is provided with a complementary label that represents a class to which the pattern does not belong. In the existing literature, complementary-label learning has been studied independently from ordinary-label learning, which assumes that each training data is provided with a label representing the class to which the pattern belongs. However, providing a complementary label should be treated as equivalent to providing the rest of all labels as candidates of the one true class. In this paper, we focus on the fact that the loss functions for one-versus-all and pairwise classifications corresponding to ordinary-label learning and complementary-label learning satisfy additivity and duality, and provide a framework that directly bridges the existing supervised learning frameworks. We also show that the complementary labels generated from a probabilistic model assumed in the existing literature is equivalent to the ordinary labels generated from a mixture of ground-truth probabilistic model and uniform distribution. Based on this finding, the relationship between our work and the existing work can be naturally derived. Further, we derive the classification risk and error bound for any loss functions that satisfy additivity and duality.

Original languageEnglish
Article number288
JournalSN Computer Science
Issue number4
Publication statusPublished - 2021 Jul


  • Complementary-label learning
  • Statistical inference
  • Statistical learning theory
  • Supervised classification

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Networks and Communications
  • Computer Science Applications
  • Computer Science(all)
  • Artificial Intelligence
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'Candidate-Label Learning: A Generalization of Ordinary-Label Learning and Complementary-Label Learning'. Together they form a unique fingerprint.

Cite this