Skip to main content
SpringerLink
Log in

Partial label learning with noisy side information

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

In Partial Label Learning (PLL), each training instance is assigned with several candidate labels, among which only one label is the ground-truth. Existing PLL methods mainly focus on identifying the unique ground-truth label, while the contribution of other candidate labels as well as the latent noisy side information are regrettably ignored. To tackle the above issues, we propose a novel PLL approach named PL-NSI, which simultaneously takes the feature noise and the contributions of other candidate labels into consideration. Specifically, given PLL data with noisy side information, we first leverage the latent label distribution to emphasize the different contributions of other candidate labels. Then, we utilize the low-rank representation to recover the ideal feature space from the corrupted observations. In addition, to improve the robustness of the final model, we adopt an extra regularization term to exploit the consistency between visual information and semantic information. Finally, we conduct enormous experiments on both artificial and real-world data sets, and the experimental results verify that our method can achieve competitive performance against state-of-the-art methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Briggs F, Fern X, Raich R (2012) Rank-loss support instance machines for miml instance annotation. In: ACM SIGKDD international conference on knowledge discovery and data mining, pp 534–542

  2. Candès E, Plan Y (2010) Matrix completion with noise. Proceedings of the IEEE 98(6):925–936

    Article  Google Scholar 

  3. Candès E, Li X, Ma Y, Wright J (2009) Robust principal component analysis? In: Journal of the ACM

  4. Chen C, Patel V, Chellappa R (2015) Matrix completion for resolving label ambiguity. In: Proceedings of the 2015 IEEE conference on computer vision and pattern recognition, pp 4110–4118

  5. Chen G, Liu T, Tang Y, Jian Y, Jie Y, Tao D (2017) A regularization approach for instance-based superset label learning. IEEE Transactions on Cybernetics 48(3):967–978

    Google Scholar 

  6. Chen Y, Patel V, Chellappa R, Phillips P (2014) Ambiguously labeled learning using dictionaries. IEEE Transactions on Information Forensics and Security 9(12):2076–2088

    Article  Google Scholar 

  7. Cour T, Sapp B, Taskar B (2011) Learning from partial labels. IEEE Transactions on Knowledge and Data Engineering 12(5):1501–1536

    MathSciNet  MATH  Google Scholar 

  8. Feng L, An B (2018) Leveraging latent label distributions for partial label learning. In: International joint conference on artificial intelligence, pp 2107–2113

  9. Feng L, An B (2019a) Partial label learning by semantic difference maximization. In: International joint conference on artificial intelligence, pp 2294–2300

  10. Feng L, An B (2019b) Partial label learning with self-guided retraining. In: Proceedings of the AAAI conference on artificial intelligence, pp 3542–3549

  11. Guillaumin M, Verbeek J, Schmid C (2010) Multiple instance metric learning from automatically labeled bags of faces. In: European conference on computer vision, pp 634–647

  12. He S, Li L (2018) Estimating latent relative labeling importances for multi-label learning. In: Proceedings of the IEEE international conference on data mining, pp 1013–1018

  13. Hullermeier E, Beringer J (2005) Learning from ambiguously labeled examples. International Symposium on Intelligent Data Analysis 10(5):168–179

    MATH  Google Scholar 

  14. Luo J, Orabona F (2010) Learning from candidate labeling sets. In: Advances in neural information processing systems, pp 1504–1512

  15. Lv J, Xu M, Feng L, Niu G, Geng X, Sugiyama M (2020) Progressive identification of true labels for partial-label learning. In: Proceedings of the international conference on machine learning, pp 6500–6510

  16. Lyu G, Feng S, Huang W, Dai G, Zhang H, Chen B (2020) Partial label learning via low-rank representation and label propagation. Soft Comput 24(7):5165–5176

    Article  Google Scholar 

  17. Lyu G, Feng S, Li Y, Jin Y, Dai G, Lang C (2020) Hera: Partial label learning by combining heterogeneous loss with sparse and low-rank regularization. ACM Transactions on Intelligent Systems and Technology 11(3):1–19

    Article  Google Scholar 

  18. Lyu G, Feng S, Li Y, Jin Y, Dai G, Lang C (2020) HERA: partial label learning by combining heterogeneous loss with sparse and low-rank regularization. ACM Transactions on Intelligent Systems and Technology 11(3):1–19

    Article  Google Scholar 

  19. Lyu G, Feng S, Wang T, Lang C (2020d) A self-paced regularization framework for partial-label learning. IEEE Transactions on Cybernetics:1–13. https://doi.org/10.1109/TCYB.2020.2990908

  20. Lyu G, Feng S, Wang T, Lang C, Li Y (2021) Gm-pll: Graph matching based partial label learning. IEEE Transactions on Knowledge and Data Engineering 33(2):521–535

    Article  Google Scholar 

  21. Nguyen N, Caruana R (2008) Classification with partial labels. In: ACM SIGKDD International conference on knowledge discovery and data mining, pp 551–559

  22. Panis G, Lanitis A (2016) An overview of research activities in facial age estimation using the fg-net aging database. Journal of American History 5(2):37–46

    Google Scholar 

  23. Wang C, Yan S, Zhang L (2009) Multi-label sparse coding for automatic image annotation. In: IEEE Conference on computer vision and pattern recognition, pp 20–25

  24. Wang D, Zhang M (2019) Adaptive graph guided disambiguation for partial label learning. In: Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining, pp 83–91

  25. Wang J, Zhang ML (2018) Towards mitigating the class-imbalance problem for partial label learning. In: ACM SIGKDD international conference on knowledge discovery and data mining, pp 2427–2436

  26. Wang Q, Zhou Z (2019) Partial label learning with unlabeled data. In: Proceedings of the international joint conference on artificial intelligence, pp 3755–3761

  27. Wu X, Zhang ML (2018) Towards enabling binary decomposition for partial label learning. In: International joint conference on artificial intelligence, pp 2868–2874

  28. Xie M, Huang S (2020) Semi-supervised partial multi-label learning. In: IEEE International conference on data mining, pp 691–700

  29. Yu F, Zhang M (2017) Maximum margin partial label learning. Machine Learning 106(4):573–593

    Article  MathSciNet  Google Scholar 

  30. Yu F, Zhang ML (2016) Maximum margin partial label learning. In: Asian conference on machine learning, pp 96–111

  31. Yu G, RangWala H, Domeniconi C, Zhang G (2013) Protein function prediction using dependence maximization. In: IEEE Conference on computer vision and pattern recognition, pp 574–589

  32. Zeng Z, Xiao S, Jia K, Chan T, Gao S, Xu D, Ma Y (2013) Learning by associating ambiguously labeled images. In: IEEE Conference on computer vision and pattern recognition, pp 708–715

  33. Zhang M, Yu F (2015) Solving the partial label learning problem: an instance-based approach. In: International joint conference on artificial intelligence, pp 4048–4054

  34. Zhang M, Yu F, Tang C (2017) Disambiguation-free partial label learning. IEEE Transactions on Knowledge and Data Engineering 29(10):2155–2167

    Article  Google Scholar 

  35. Zhang ML (2014) Disambiguation-free partial label learning. In: Proceedings of the 2014 SIAM international conference on data mining, pp 37–45

  36. Zhou Y, He J, Gu H (2016) Partial label learning via gaussian processes. IEEE Transactions on Cybernetics 47(12):4443–4450

    Article  Google Scholar 

  37. Zhu G, Yan S, Ma Y (2010) Image tag refinement towards low-rank, content-tag prior and error sparsity. In: Proceedings of the ACM international conference on multimedia, pp 461–470

Download references

Acknowledgements

A preliminary version of this paper has been published as [17] and [20]. The work was supported by the Natural Science Foundation of Beijing Municipality (4202058).

Author information

Authors and Affiliations

  1. School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China

    Shaokai Wang, Mingxuan Xia, Zilong Wang, Gengyu Lyu & Songhe Feng

Authors
  1. Shaokai Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mingxuan Xia
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zilong Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Gengyu Lyu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Songhe Feng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Songhe Feng.

Additional information

Publisher's note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Shaokai Wang and Mingxuan Xia contributed equally to this work.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, S., Xia, M., Wang, Z. et al. Partial label learning with noisy side information. Appl Intell 52, 12382–12396 (2022). https://doi.org/10.1007/s10489-021-03137-0

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-021-03137-0

Keywords

Search

Navigation