Skip to main content
SpringerLink
Log in

Learning with partial multi-labeled data by leveraging low-rank constraint and decomposition

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Partial Multi-label Learning (PML) refers to the task of learning from the noisy data that are annotated with candidate labels but only some of them are valid. To resolve it, the existing methods recover the accurate supervision from candidate labels by estimating the ground-truth confidence, while inducing the prediction model with it. Generally speaking, the performance of PML methods is dominated by the quality of the ground-truth confidence estimation. In this paper, we propose a novel PML method, namely Partial Multi-label Learning with Low-rank Constraint and Decomposition (PML-lcd). Specifically, we not only compute the low-rank approximation of the candidate label matrix, but also decompose the approximation into a low-rank ground-truth confidence matrix and a noisy matrix, i.e., an auxiliary matrix defined to capture noisy irrelevant labels. The objective of PML-lcd can be efficiently solved by alternating direction method of multipliers. Experimental results validate that PML-lcd performs better and more stable than the state-of-the-art baselines with different noise levels.

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

Similar content being viewed by others

Notes

  1. In this work, we fix τ1 and τ2 to 1.

  2. The datasets are available at the mulan website “http://mulan.sourceforge.net/datasets-mlc.html”

  3. http://palm.seu.edu.cn/zhangml/files/PARTICLE.rar

  4. http://palm.seu.edu.cn/zhangml/files/ML-kNN.rar

  5. http://palm.seu.edu.cn/zhangml/files/LIFT.rar

References

  1. Balasubramanian K, Lebanon G (2012) The landmark selection method for multiple output prediction. In: International conference on machine learning, pp 283–290

  2. Boyd S, Parikh N, Chu E, Peleato B, Eckstein J (2011) Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations Trends Mach Learn 3(1):1–122

    Article  MATH  Google Scholar 

  3. Cai JF, Candès EJ, Sheni Z (2010) A singular value thresholding algorithm for matrix completion. SIAM J Optim 20(4):1956–1982

    Article  MathSciNet  MATH  Google Scholar 

  4. Chen YN, Weng W, Wu SX, Chen BH, Fan YL, Liu JH (2021) An efficient stacking model with label selection for multi-label classification. Appl Intell 51(1):308–325

    Article  Google Scholar 

  5. Clare A, King RD (2001) Knowledge discovery in multi-label phenotype data. In: European conference on principles of data mining and knowledge discovery, pp 42–53

  6. collab=Demšar, J. (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1–30

    MathSciNet  MATH  Google Scholar 

  7. Elisseeff A, Weston J (2002) A kernel method for multi-labelled classification. In: Advances in neural information processing systems, pp 681–687

  8. Fang JP, Zhang ML (2019) Partial multi-label learning via credible label elicitation. In: AAAI conference on artificial intelligence, pp 1–8

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

  10. Gong C, Liu T, Tang Y, Yang J, Yang J, Tao D (2018) A regularization approach for instance-based superset label learning. IEEE Trans Cybern 48(3):967–978

    Article  Google Scholar 

  11. Guo A, Wu J, Sheng VS, Zhao P, Cui Z (2017) Multi-label active learning with low-rank mapping for image classification. In: IEEE international conference on multimedia and expo, pp 259–264

  12. Hsu DJ, Kakade SM, Langford J, Zhang T (2009) Multilabel prediction via compressed sensing. In: Neural information processing systems, pp 772–780

  13. Li C, Li X, Ouyang J (2020) Learning with noisy partial labels by simultaneously leveraging global and local consistencies. In: ACM international conference on information and knowledge management, pp 725–734

  14. Li C, Li X, Ouyang J, Wang Y (2020) Detecting the fake candidate instances: ambiguous label learning with generative adversarial networks. In: ACM international conference on information and knowledge management, pp 903–912

  15. Li X, Wang Y (2020) Recovering accurate labeling information from partially valid data for effective multi-label learning. In: International joint conference on artificial intelligence, pp 1373–1380

  16. Li X, Wang Y, Zhang Z, Hong R, Wang M (2021) Rmor-aion: robust multi-output regression by simultaneously alleviating input and output noises. IEEE Trans Neural Netw Learn Syst 32(3):1351–1364

    Article  MathSciNet  Google Scholar 

  17. Li Z, Lyu G, Feng S (2020) Partial multi-label learning via multi-subspace representation. In: International joint conference on artificial intelligence, pp 2612–2618

  18. Liu X, Sun L, Feng S (2022) Incomplete multi-view partial multi-label learning. Appl Intell 52:3289–3302

    Article  Google Scholar 

  19. Lyu G, Feng S, Li Y (2021) Noisy label tolerance: a new perspective of partial multi-label learning. Inf Sci 543:454–466

    Article  MathSciNet  MATH  Google Scholar 

  20. Read J, Pfahringer B, Holmes G, Frank E (2011) Classifier chains for multi-label classification, vol 85

  21. Sun L, Feng S, Wang T, Lang C, Jin Y (2019) Partial multi-label learning with low-rank and sparse decomposition. In: AAAI conference on artificial intelligence, pp 1–8

  22. Tai F, Lin HT (2012) Multilabel classification with principal label space transformation. Neural Comput 24(9):2508–2542

    Article  MathSciNet  MATH  Google Scholar 

  23. Tsoumakas G, Katakis I, Vlahavas I (2011) Random k-labelsets for multi-label classification. IEEE Trans Knowl Data Eng 23(7):1079–1089

    Article  Google Scholar 

  24. Wang H, Liu W, Zhao Y, Zhang C, Hu T, Chen G (2019) Discriminative and correlative partial multi-label learning. In: International joint conference on artificial intelligence, pp 3691–3697

  25. Wang K (2019) Robust embedding framework with dynamic hypergraph fusion for multi-label classification. In: IEEE international conference on multimedia and expo, pp 982–987

  26. Wright J, Ganesh A, Rao S, Peng Y, Ma Y (2009) Robust principal component analysis: exact recovery of corrupted low-rank matrices via convex optimization. In: Advances in neural information processing systems, pp 2080–2088

  27. Wu J, Guo A, Sheng VS, Zhao P, Cui Z, Li H (2017) Adaptive low-rank multi-label active learning for image classification. In: ACM international conference on multimedia, pp 1336–1344

  28. Xie MK, Huang SJ (2018) Partial multi-label learning. In: AAAI conference on artificial intelligence, pp 4302–4309

  29. Xie MK, Huang SJ (2020) Partial multi-label learning with noisy label identification. In: AAAI conference on artificial intelligence, pp 6454–6461

  30. Xu C, Tao D, Xu C (2016) Robust extreme multi-label learning. In: ACM SIGKDD international conference on knowledge discovery and data mining, pp 1275–1284

  31. Xu N, Liu YP, Geng X (2020) Partial multi-label learning with label distribution. In: AAAI Conference on artificial intelligence, pp 6510–6517

  32. Yu G, Chen X, Domeniconi C, Wang J, Li Z, Zhang Z, Wu X (2018) Feature-induced partial multi-label learning. In: IEEE international conference on data mining, pp 1398–1403

  33. Yu HF, Jain P, Kar P, Dhillon I (2014) Large-scale multi-label learning with missing labels. In: International conference on machine learning, pp 593–601

  34. Zhang ML, Li YK, Liu XY, Geng X (2018) Binary relevance for multi-label learning: an overview. Frontiers Comput Sci 12(2):191–202

    Article  Google Scholar 

  35. Zhang ML, Wu L (2015) Lift: multi-label learning with label-specific features. IEEE Trans Pattern Anal Mach Intell 37(11):107–120

    Article  Google Scholar 

  36. Zhang ML, Zhou ZH (2007) Ml-knn: a lazy learning approach to multi-label learning. Pattern Recogn 40(7):2038–2048

    Article  MATH  Google Scholar 

  37. Zhang ML, Zhou ZH (2014) A review on multi-label learning algorithms. IEEE Trans Knowl Data Eng 26(8):1819–1837

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by the National Natural Science Foundation of China (NSFC) No.51805203.

Author information

Authors and Affiliations

  1. College of Computer Science and Technology, Jilin University, Jilin, China

    Ying Wang, Yuanyuan Guan, Bing Wang & Ximing Li

  2. Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Jilin, China

    Ying Wang, Yuanyuan Guan, Bing Wang & Ximing Li

Authors
  1. Ying Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yuanyuan Guan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Bing Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ximing Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ximing Li.

Ethics declarations

Conflict of Interests

The authors declare that they have no conflict of interest.

Additional information

Publisher’s note

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

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, Y., Guan, Y., Wang, B. et al. Learning with partial multi-labeled data by leveraging low-rank constraint and decomposition. Appl Intell 53, 8133–8145 (2023). https://doi.org/10.1007/s10489-022-03989-0

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-03989-0

Keywords

Search

Navigation