Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
Springer Nature Link
Log in

Feature selection for label distribution learning under feature weight view

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

Label Distribution Learning (LDL) is a fine-grained learning paradigm that addresses label ambiguity, yet it confronts the curse of dimensionality. Feature selection is an effective method for dimensionality reduction, and several algorithms have been proposed for LDL that tackle the problem from different views. In this paper, we propose a novel feature selection method for LDL. First, an effective LDL model is trained through a classical LDL loss function, which is composed of the maximum entropy model and KL divergence. Then, to select common and label-specific features, their weights are enhanced by \(l_{21}\)-norm and label correlation, respectively. Considering that direct constraint on the parameter by label correlation will make the label-specific features between relevant labels tend to be the same, we adopt the strategy of constraining the maximum entropy output model. Finally, the proposed method will introduce Mutual Information (MI) for the first time in the optimization model for LDL feature selection, which distinguishes similar features thus reducing the influence of redundant features. Experimental results on twelve datasets validate the effectiveness of the proposed method.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data availability

The relevant experimental data are available from a repository, i.e., http://palm.seu.edu.cn/xgeng/LDL/index.htm.

Notes

  1. https://archive-beta.ics.uci.edu/datasets.

  2. http://palm.seu.edu.cn/xgeng/LDL/index.htm.

References

  1. Wang J, Geng X (2023) Label distribution learning by exploiting label distribution manifold. IEEE Trans Neural Netw Learn Syst 34(2):839–852

    Article  Google Scholar 

  2. Dong X, Luo T, Fan R et al (2023) Active label distribution learning via kernel maximum mean discrepancy. Front Comp Sci 17(4):174327

    Article  Google Scholar 

  3. Wang J, Geng X (2021) Label distribution learning machine. In: International Conference on Machine Learning, pp 10749–10759

  4. Tan C, Chen S, Geng X et al (2023) A label distribution manifold learning algorithm. Pattern Recogn 135:109112

    Article  Google Scholar 

  5. Geng X (2016) Label distribution learning. IEEE Trans Knowl Data Eng 28(7):1734–1748

    Article  Google Scholar 

  6. Li W, Lu Y, Chen L et al (2022) Label distribution learning with noisy labels via three-way decisions. Int J Approx Reason 150:19–34

    Article  MathSciNet  Google Scholar 

  7. Jia X, Shen X, Li W et al (2023) Label distribution learning by maintaining label ranking relation. IEEE Trans Knowl Data Eng 35(2):1695–1707

    Google Scholar 

  8. Geng X, Qian X, Huo Z et al (2020) Head pose estimation based on multivariate label distribution. IEEE Trans Pattern Anal Mach Intell 44(4):1974–1991

    Article  Google Scholar 

  9. Zhang H, Zhang Y, Geng X (2021) Practical age estimation using deep label distribution learning. Front Comp Sci 15:1–6

    Google Scholar 

  10. Le N, Nguyen K, Tran Q, et al (2023) Uncertainty-aware label distribution learning for facial expression recognition. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp 6088–6097

  11. Nishio M, Matsuo H, Kurata Y et al (2023) Label distribution learning for automatic cancer grading of histopathological images of prostate cancer. Cancers 15(5):1535

    Article  Google Scholar 

  12. Wang J, Zhang F, Jia X et al (2022) Multi-class asd classification via label distribution learning with class-shared and class-specific decomposition. Med Image Anal 75:102294

    Article  Google Scholar 

  13. Ma H, Lu N, Mei J et al (2023) Label distribution learning for scene text detection. Front Comp Sci 17(6):176339

    Article  Google Scholar 

  14. Li H, Huang G, Li Y et al (2022) Concept-based label distribution learning for text classification. Int J Comput Intell Syst 15(1):85

    Article  Google Scholar 

  15. Lin Y, Liu H, Zhao H et al (2023) Hierarchical feature selection based on label distribution learning. IEEE Trans Knowl Data Eng 35(6):5964–5976

    Google Scholar 

  16. Liu J, Lin Y, Du J et al (2023) Asfs: a novel streaming feature selection for multi-label data based on neighborhood rough set. Appl Intell 53(2):1707–1724

    Article  Google Scholar 

  17. Liu J, Lin Y, Ding W et al (2022) Fuzzy mutual information-based multilabel feature selection with label dependency and streaming labels. IEEE Trans Fuzzy Syst 31(1):77–91

    Article  Google Scholar 

  18. Qian W, Xiong Y, Yang J et al (2022) Feature selection for label distribution learning via feature similarity and label correlation. Inf Sci 582:38–59

    Article  MathSciNet  Google Scholar 

  19. Ren T, Jia X, Li W, et al (2019) Label distribution learning with label-specific features. In: IJCAI, pp 3318–3324

  20. Gao W, Li Y, Hu L (2021) Multilabel feature selection with constrained latent structure shared term. IEEE Trans Neural Netw Learn Syst. https://doi.org/10.1109/TNNLS.2021.3105142

    Article  Google Scholar 

  21. Gao W, Hu L, Zhang P (2020) Feature redundancy term variation for mutual information-based feature selection. Appl Intell 50:1272–1288

    Article  Google Scholar 

  22. Gao W, Hao P, Wu Y et al (2023) A unified low-order information-theoretic feature selection framework for multi-label learning. Pattern Recogn 134:109111

    Article  Google Scholar 

  23. Xiong C, Qian W, Wang Y et al (2021) Feature selection based on label distribution and fuzzy mutual information. Inf Sci 574:297–319

    Article  MathSciNet  Google Scholar 

  24. Zhang J, Lin Y, Jiang M, et al (2020) Multi-label feature selection via global relevance and redundancy optimization. In: IJCAI, pp 2512–2518

  25. Cohen I, Huang Y, Chen J et al (2009) Pearson correlation coefficient. Noise reduction in speech processing. Springer, pp 1–4

    Chapter  Google Scholar 

  26. Zhang J, Wu H, Jiang M et al (2023) Group-preserving label-specific feature selection for multi-label learning. Expert Syst Appl 213:118861

    Article  Google Scholar 

  27. Li W, Chen J, Lu Y, et al (2022) Filling missing labels in label distribution learning by exploiting label-specific feature selection. In: 2022 International Joint Conference on Neural Networks (IJCNN), pp 1–8

  28. Huang J, Li G, Huang Q et al (2017) Joint feature selection and classification for multilabel learning. IEEE Trans Cybern 48(3):876–889

    Article  MathSciNet  Google Scholar 

  29. Argyriou A, Evgeniou T, Pontil M (2006) Multi-task feature learning. Advances in neural information processing systems 19

  30. Sun L, Feng S, Liu J et al (2021) Global-local label correlation for partial multi-label learning. IEEE Trans Multimedia 24:581–593

    Article  Google Scholar 

  31. Zhao D, Gao Q, Lu Y et al (2022) Learning multi-label label-specific features via global and local label correlations. Soft Comput 26(5):2225–2239

    Article  Google Scholar 

  32. Kraskov A, Stögbauer H, Grassberger P (2004) Estimating mutual information. Phys Rev E 69(6):066138

    Article  MathSciNet  Google Scholar 

  33. Ross BC (2014) Mutual information between discrete and continuous data sets. PLoS ONE 9(2):e87357

    Article  Google Scholar 

  34. Gonçalves EC, Plastino A, Freitas AA (2013) A genetic algorithm for optimizing the label ordering in multi-label classifier chains. In: 2013 IEEE 25th International Conference on Tools with Artificial Intelligence, pp 469–476

  35. Tsoumakas G, Katakis I, Vlahavas I (2008) Effective and efficient multilabel classification in domains with large number of labels. In: Proc. ECML/PKDD 2008 Workshop on Mining Multidimensional Data (MMD’08), pp 53–59

  36. Briggs F, Lakshminarayanan B, Neal L et al (2012) Acoustic classification of multiple simultaneous bird species: a multi-instance multi-label approach. J Acoust Soc Am 131(6):4640–4650

    Article  Google Scholar 

  37. Xu J, Liu J, Yin J et al (2016) A multi-label feature extraction algorithm via maximizing feature variance and feature-label dependence simultaneously. Knowl-Based Syst 98:172–184

    Article  Google Scholar 

  38. Xu N, Liu YP, Geng X (2019) Label enhancement for label distribution learning. IEEE Trans Knowl Data Eng 33(4):1632–1643

    Article  Google Scholar 

  39. Zhang Y, Zhou ZH (2010) Multilabel dimensionality reduction via dependence maximization. ACM Trans Knowl Discov Data (TKDD) 4(3):1–21

    Article  Google Scholar 

  40. Zhang J, Luo Z, Li C et al (2019) Manifold regularized discriminative feature selection for multi-label learning. Pattern Recogn 95:136–150

    Article  Google Scholar 

  41. Kashef S, Nezamabadi-pour H, Nikpour B (2018) Multilabel feature selection: a comprehensive review and guiding experiments. Wiley Interdiscip Rev Data Min Knowl Discov 8(2):e1240

    Article  Google Scholar 

  42. Demiar J, Schuurmans D (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7(1):1–30

    MathSciNet  Google Scholar 

Download references

Acknowledgements

This work was supported by the National Natural Science Foundation of China through grant No. 62076116, the Natural Science Foundation of Fujian Province through grant No. 2021J02049, and the Open Project Program of Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry, Wuyi University through grant No. FKLBDAITI202202.

Author information

Authors and Affiliations

  1. School of Computer Science, Minnan Normal University, Zhangzhou, 363000, Fujian, China

    Shidong Lin, Chenxi Wang, Yu Mao & Yaojin Lin

  2. Key Laboratory of Data Science and Intelligence Application, Minnan Normal University, Zhangzhou, 363000, Fujian, China

    Shidong Lin, Chenxi Wang, Yu Mao & Yaojin Lin

Authors
  1. Shidong Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chenxi Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yu Mao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yaojin Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yaojin Lin.

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 (e.g. a society or other partner) 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

Lin, S., Wang, C., Mao, Y. et al. Feature selection for label distribution learning under feature weight view. Int. J. Mach. Learn. & Cyber. 15, 1827–1840 (2024). https://doi.org/10.1007/s13042-023-02000-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-023-02000-7

Keywords

Search

Navigation