Skip to main content
SpringerLink
Log in

Robust semi non-negative low-rank graph embedding algorithm via the L21 norm

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

The non-negative matrix factorization (NMF) method is applied in many fields, including pattern recognition, visual analysis, and biomedicine. However, existing NMF methods acquire low dimensional representation directly from high dimensional data, and the low-rank part of the data contains the most useful information. Furthermore, the NMF method is vulnerable to noise interference and is not adequately robust. Therefore, a robust semi non-negative low-rank graph embedding algorithm via the L21 norm (RSNLGEL21) is proposed to address the stated problems. The algorithm considers the effective low-rank structure and geometric information of the original data and constrains the coefficient matrix to be non-negative; however, it does not impose a non-negative constraint on the base matrix. In addition, the L21 norm is introduced into the graph embedding and data reconstruction functions slightly to improve its recognition ability and robustness. Moreover, this paper also provides an iterative formula to the RSNLGEL21 algorithm and the corresponding proof of convergence and to analyze its computational complexity. Experiments on the ORL, FEI, AR, and FERET image datasets shows that the RSNLGEL21 algorithm has certain advantages in clustering performance.

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
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  1. Lee DD, Seung HS (1999) Learning the parts of objects by non-negative matrix factorization. Nature 401(6755):788–791

    Article  Google Scholar 

  2. Lee DD, Seung HS (2000) Algorithms for non-negative matrix factorization. In: 2000 Advances in neural information processing systems (NIPS), pp 556–562

  3. Gurve D, Delisle-Rodriguez D, Romero-Laiseca M et al (2020) Subject-specific EEG channel selection using non-negative matrix factorization for lower-limb motor imagery recognition. J Neural Eng 17(2):026029.1–026029.15

  4. Li DG, Chen X, Li HL et al (2019) Manifold regularized sparse constraint non-negative matrix factorization with superpixel algorithm for hyperspectral unmixing. J Comp Appl 39(10):3100–3106

    Google Scholar 

  5. Hu LR, Jia SY, Wu N (2020) Face recognition based on linear projective non-negative matrix factorization with Kullback-Leibler divergence. J Phys Conf Series 1437(1):012111

    Article  Google Scholar 

  6. Zhao Y, Chen X, Yin J et al (2020) SNMFSMMA: using symmetric non-negative matrix factorization and Kronecker regularized least squares to predict potential small molecule-microRNA association. RNA Biol 17(2):281–291

    Article  Google Scholar 

  7. Jiang W, Ma TT, Feng XT et al (2020) Robust semi non-negative matrix factorization with adaptive graph regularization for gene representation. Chin J Electron 29(1):122–131

    Article  Google Scholar 

  8. Bakal G, Kilicoglu H, Kavuluru R (2019) Non-negative matrix factorization for drug repositioning: experiments with the repoDB dataset. AMIA Symposium 2019:238–247

    Google Scholar 

  9. Peng SY, Ser W, Chen BD et al (2020) Robust non-negative matrix factorization with local coordinate constraint for image clustering. Eng Appl Artif Intell 88:103354.1–103354.12.

  10. Shu ZQ, Zhang YM, Li P et al (2020) Dual local learning regularized non-negative matrix factorization and its semi supervised extension for clustering. Neural Comput Appl 1–19

  11. Peng SY, Ser W, Chen BD et al (2020) Robust semi supervised non-negative matrix factorization for image clustering. Pattern Recogn 111:107683–107694

    Article  Google Scholar 

  12. Leng CC, Zhang H, Cai GR et al (2019) Graph regularized Lp smooth non-negative matrix factorization for data representation. IEEE/CAA J Automatica Sinica 6(2):584–595

    Article  MathSciNet  Google Scholar 

  13. Li XL, Cui GS, Dong YS (2017) Graph regularized non-negative low-rank matrix factorization for image clustering. IEEE Trans Cybern 47(11):3840–3853

    Article  MathSciNet  Google Scholar 

  14. Ding CHQ, Li T, Jordan MI (2010) Convex and semi non-negative matrix factorizations. IEEE Trans Pattern Anal Mach Intell 32(1):45–55

    Article  Google Scholar 

  15. Cai D, He XF, Han JW et al (2011) Graph regularized non-negative matrix factorization for data representation. IEEE Trans Pattern Anal Mach Intell 33(8):1548–1560

    Article  Google Scholar 

  16. Xiong H, Guo YQ, Zhu HH et al (2018) Robust non-negative matrix factorization on manifold via projected gradient method. Inf Control 47(2):166–175

    Google Scholar 

  17. Yang J, Yang S, Fu Y et al (2008) Non-negative graph embedding. In: 2008 IEEE conference on computer vision and pattern recognition (CCVPR), pp 1–8

  18. Wang CH, Song Z, Yan SC et al (2009) Multiplicative non-negative graph embedding. In: 2009 IEEE computer society conference on computer vision and pattern recognition workshops (CVPR), pp 389–396

  19. Liu XB, Yan SC, Jin H (2010) Projective non-negative graph embedding. IEEE Trans Image Process 19(5):1126–1137

    Article  MathSciNet  Google Scholar 

  20. Zhang HW, Zha ZJ, Yang Y et al (2014) Robust (semi) non-negative graph embedding. IEEE Trans Image Process 23(7):2996–3012

    Article  MathSciNet  Google Scholar 

  21. Cui JR, Wen JJ, Li ZM et al (2015) Discriminant non-negative graph embedding for face recognition. Neurocomputing 149(c):1451–1460

    Article  Google Scholar 

  22. Liu J , Zhang H, Liu BD et al (2016) Face clustering based on graph embedded semi-NMF with kernels. In: 2016 IEEE 13th International Conference on Signal Processing (ICSP), pp 777–782

  23. Dutta A, Sahbi H (2019) Stochastic graphlet embedding. Neural Netw Learn Syst, IEEE Trans on 30(8):2369–2382

    Article  MathSciNet  Google Scholar 

  24. Liu GQ, Lu GF, Zhou S et al (2020) Non-negative low rank graph embedding algorithm. J Front Comput Sci Technol 138(03):147–157

    Google Scholar 

  25. Wright J, Ganesh A, Rao S et al (2009) Robust principal component analysis: exact recovery of corrupted low rank matrices via convex optimization. In: 2009 Advances in Neural Information Processing Systems 22: Conference on Neural Information Processing Systems A Meeting Held December (NIPS), pp 2080–2088

  26. Belkin M, Niyogi P (2003) Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput 15(6):1373–1396

    Article  Google Scholar 

  27. Roweis S, Saul L (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500):2323–2326

    Article  Google Scholar 

  28. Yan S, Xu D, Zhang B et al (2007) Graph embedding and extensions: a general framework for dimensionality reduction. IEEE Trans Pattern Anal Mach Intell 29(1):40–51

    Article  Google Scholar 

  29. Zhou TY, Tao DC (2011) Godec: randomized low rank & sparse matrix decomposition in noisy case.In: 2011 International conference on machine learning (ICML), pp 33–40

  30. Roweis ST (1997) EM algorithms for PCA and SPCA. In: 1997 Advances in neural information processing systems (NIPS), pp 626–632

  31. Chung FR (1997) Spectral graph theory, Providence, RI, USA: Amer. Math. Soc

  32. Jolliffe IT (2002) Principal component analysis. J Mark Res 87(4):513

    MATH  Google Scholar 

  33. Wu BL, Wang Y En, Zhu Zh et al (2018) Manifold NMF with L21 norm for clustering. Neurocomputing 78–88

Download references

Acknowledgements

This paper is supported by the Graduate Innovation Foundation of Jiangsu Province under Grant No. KYLX16_0781, the Natural Science Foundation of Jiangsu Province under Grants No. BK20181340, the 111 Project under Grants No. B12018, and PAPD of Jiangsu Higher Education Institutions.

Author information

Authors and Affiliations

  1. School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi Jiangsu, 214122, China

    Guoqing Liu, Hongwei Ge,  JinlongYang & Shuangxi Wang

  2. Key Laboratory of Advanced Process Control for Light Industry (Jiangnan University), Ministry of Education, Wuxi, 214122, China

    Guoqing Liu, Hongwei Ge,  JinlongYang & Shuangxi Wang

Authors
  1. Guoqing Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hongwei Ge
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. JinlongYang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shuangxi Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hongwei Ge.

Additional information

Publisher's note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, G., Ge, H., JinlongYang et al. Robust semi non-negative low-rank graph embedding algorithm via the L21 norm. Appl Intell 52, 8708–8720 (2022). https://doi.org/10.1007/s10489-021-02837-x

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-021-02837-x

Keywords

Search

Navigation