Abstract
Complementary-Label Learning (CLL) is a weakly-supervised learning problem that aims to learn a multi-class classifier from only complementary labels, which indicate a class to which an instance does not belong. Existing approaches mainly adopt the paradigm of reduction to ordinary classification, which applies specific transformations and surrogate losses to connect CLL back to ordinary classification. Those approaches, however, face several limitations, such as the tendency to overfit. In this paper, we sidestep those limitations with a novel perspective–reduction to probability estimates of complementary classes. We prove that accurate probability estimates of complementary labels lead to good classifiers through a simple decoding step. The proof establishes a reduction framework from CLL to probability estimates. The framework offers explanations of several key CLL approaches as its special cases and allows us to design an improved algorithm that is more robust in noisy environments. The framework also suggests a validation procedure based on the quality of probability estimates, offering a way to validate models with only CLs. The flexible framework opens a wide range of unexplored opportunities in using deep and non-deep models for probability estimates to solve CLL. Empirical experiments further verified the framework’s efficacy and robustness in various settings. The full paper can be accessed at https://arxiv.org/abs/2209.09500.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chou, Y.T., Niu, G., Lin, H.T., Sugiyama, M.: Unbiased risk estimators can mislead: a case study of learning with complementary labels. In: International Conference on Machine Learning, pp. 1929–1938. PMLR (2020)
Gao, Y., Zhang, M.L.: Discriminative complementary-label learning with weighted loss. In: International Conference on Machine Learning, pp. 3587–3597. PMLR (2021)
Ishida, T., Niu, G., Hu, W., Sugiyama, M.: Learning from complementary labels. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 5644–5654 (2017)
Ishida, T., Niu, G., Menon, A., Sugiyama, M.: Complementary-label learning for arbitrary losses and models. In: International Conference on Machine Learning, pp. 2971–2980. PMLR (2019)
Kull, M., Flach, P.: Novel decompositions of proper scoring rules for classification: score adjustment as precursor to calibration. In: Appice, A., Rodrigues, P.P., Santos Costa, V., Soares, C., Gama, J., Jorge, A. (eds.) ECML PKDD 2015. LNCS (LNAI), vol. 9284, pp. 68–85. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-23528-8_5
Li, X., Liu, T., Han, B., Niu, G., Sugiyama, M.: Provably end-to-end label-noise learning without anchor points. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 6403–6413. PMLR (18–24 Jul 2021)
Liu, J., Hang, H., Wang, B., Li, B., Wang, H., Tian, Y., Shi, Y.: GAN-CL: generative adversarial networks for learning from complementary labels. IEEE Trans. Cybernet. (2021)
Wang, D.B., Feng, L., Zhang, M.L.: Learning from complementary labels via partial-output consistency regularization. In: IJCAI, pp. 3075–3081 (2021)
Williamson, R.C., Vernet, E., Reid, M.D.: Composite multiclass losses. J. Mach. Learn. Res. 17(222), 1–52 (2016)
Xu, Y., Gong, M., Chen, J., Liu, T., Zhang, K., Batmanghelich, K.: Generative-discriminative complementary learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 6526–6533 (2020)
Yu, X., Liu, T., Gong, M., Tao, D.: Learning with biased complementary labels. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 68–83 (2018)
Zhang, M., Lee, J., Agarwal, S.: Learning from noisy labels with no change to the training process. In: International Conference on Machine Learning, pp. 12468–12478. PMLR (2021)
Zhang, Y., Liu, F., Fang, Z., Yuan, B., Zhang, G., Lu, J.: Learning from a complementary-label source domain: theory and algorithms. IEEE Trans. Neural Netw. Learn. Syst. (2021)
Zhou, Z.H.: A brief introduction to weakly supervised learning. Nat. Sci. Rev. 5(1), 44–53 (2018)
Acknowlegement
We thank the anonymous reviewers and the members of NTU CLLab for valuable suggestions. The work is partially supported by the National Science and Technology Council via the grants 110-2628-E-002-013 and 111-2628-E-002-018. We also thank the National Center for High-performance Computing (NCHC) of National Applied Research Laboratories (NARLabs) in Taiwan for providing computational resources.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lin, WI., Lin, HT. (2023). Reduction from Complementary-Label Learning to Probability Estimates. In: Kashima, H., Ide, T., Peng, WC. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2023. Lecture Notes in Computer Science(), vol 13936. Springer, Cham. https://doi.org/10.1007/978-3-031-33377-4_36
Download citation
DOI: https://doi.org/10.1007/978-3-031-33377-4_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33376-7
Online ISBN: 978-3-031-33377-4
eBook Packages: Computer ScienceComputer Science (R0)