Abstract
Tensor factorization has been widely applied in computer vision and machine learning area. Nonnegative Tucker decomposition (NTD) is a popular tensor factorization technique. However, it neglects the geometrical structure of the data space and the available label information of sample data, lowering the data representation performance. To overcome this defect, in this paper, we propose a novel semi-supervised NTD method, named graph regularized discriminative nonnegative Tucker decomposition (GDNTD), which incorporates the graph construction of the data space and the available label information of the sample data into NTD. Specifically, a graph construction is utilized to preserve the geometric structure between data by a graph regularization term. Then, a label matrix is presented for guiding the data representation by a label constraint regularization term. Finally, based on the NTD property of maintaining the internal structure of data, the graph regularizer and the label regularizer are integrated into NTD to generate the proposed method. Thus, GDNTD can extract the part-based representation, preserve the local geometrical structure of the data space, and improve the discriminative ability of the learned model simultaneously, greatly boosting the model’s data representation performance. We test the proposed method through a set of evaluations on four image datasets. Experimental results show that the GDNTD method outperforms state-of-the-art approaches, demonstrating its strong potential for data representation.
Similar content being viewed by others
References
Babaee M, Tsoukalas S, Babaee M et al (2016) Discriminative nonnegative matrix factorization for dimensionality reduction. Neurocomputing 173:212–223
Cai D, He X, Han J et al (2010) Graph regularized nonnegative matrix factorization for data representation. IEEE Trans Pattern Anal Mach Intell 33(8):1548–1560
Chen B, Guan J, Li Z (2022) Unsupervised feature selection via graph regularized nonnegative CP decomposition. IEEE Trans Pattern Anal Mach Intell 45(2):2582–2594
Chung FR, Graham FC (1997) Spectral graph theory, vol 92. American Mathematical Soc
Cui G, Zhu L, Gui L et al (2020) Multidimensional clinical data denoising via bayesian CP factorization. Sci China Tech Sci 63(2):249–254
Gao W, Ma Z, Yuan X (2022) Dimensionality reduction algorithm of tensor data based on orthogonal Tucker decomposition and local discrimination difference. Appl Intell 52(12):14,518–14,540
Geng B, Tao D, Xu C et al (2012) Ensemble manifold regularization. IEEE Trans Pattern Anal Mach Intell 34(6):1227–1233
He P, Zhou G, Zhang M et al (2022) Improving temporal knowledge graph embedding using tensor factorization. Appl Intell. https://doi.org/10.1007/s10489-021-03149-w
Huang Z, Zhou G, Qiu Y et al (2022) A dynamic hypergraph regularized non-negative Tucker decomposition framework for multiway data analysis. Int J Mach Learn Cybern 13(12):3691–3710
Ioannidis VN, Zamzam AS, Giannakis GB et al (2019) Coupled graphs and tensor factorization for recommender systems and community detection. IEEE Trans Knowl Data Eng 33(3):909–920
Jia Y, Kwong S, Hou J et al (2019) Semi-supervised non-negative matrix factorization with dissimilarity and similarity regularization. IEEE Trans Neural Netw Learn Syst 31(7):2510–2521
Jiang B, Ding C, Tang J et al (2018) Image representation and learning with graph-laplacian Tucker tensor decomposition. IEEE Trans Cybern 49(4):1417–1426
Jing P, Su Y, Li Z et al (2019) Low-rank regularized tensor discriminant representation for image set classification. Signal Process 156:62–70
Jing P, Li Y, Li X et al (2021) Joint nuclear-and \({\ell }_{2,1}\)-norm regularized heterogeneous tensor decomposition for robust classification. Neurocomputing 464:317–329
Kim YD, Choi S (2007) NonnegativeTucker decomposition. In: 2007 IEEE conference on computer vision and pattern recognition, IEEE, pp 1–8
Kolda TG, Bader BW (2009) Tensor decompositions and applications. SIAM Review 51(3):455–500
Lee D, Seung HS (1999) Learning the parts of objects by non-negative matrix factorization. Nature 401(6755):788–791
Lee D, Seung HS (2000) Algorithms for non-negative matrix factorization. Adv Neural Inf Process Syst 13
Li H, Zhang J, Shi G et al (2017) Graph-based discriminative nonnegative matrix factorization with label information. Neurocomputing 266:91–100
Li X, Ng MK, Cong G et al (2016) MR-NTD: Manifold regularization nonnegative Tucker decomposition for tensor data dimension reduction and representation. IEEE Trans Neural Netw Learn Syst 28(8):1787–1800
Liang N, Yang Z, Li Z et al (2022) Incomplete multi-view clustering with incomplete graph-regularized orthogonal non-negative matrix factorization. Appl Intell 52(13):1–17
Liu Q, Lu L, Chen Z (2022) Nonnegative Tucker decomposition with graph regularization and smooth constraint for clustering. Available at SSRN 4252889
Liu Y, Ng MK (2022) Deep neural network compression by Tucker decomposition with nonlinear response. Knowl-Based Syst 241(108):171
Nocedal J, Wright SJ (1999) Numerical optimization. Springer
Pan J, Ng MK, Liu Y et al (2021) Orthogonal nonnegative Tucker decomposition. SIAM J Sci Comput 43(1):B55–B81
Qi GJ, Luo J (2020) Small data challenges in big data era: A survey of recent progress on unsupervised and semi-supervised methods. IEEE Trans Pattern Anal Mach Intell 44(4):2168–2187
Qiu Y, Zhou G, Zhang Y et al (2019) Graph regularized nonnegative Tucker decomposition for tensor data representation. ICASSP 2019–2019 IEEE International Conference on Acoustics. Speech and Signal Processing (ICASSP), IEEE, pp 8613–8617
Qiu Y, Zhou G, Wang Y et al (2020) A generalized graph regularized nonnegative Tucker decomposition framework for tensor data representation. IEEE Trans Cybern 52(1):594–607
Qiu Y, Zhou G, Chen X et al (2021) Semi-supervised non-negative Tucker decomposition for tensor data representation. Sci China Tech Sci 64(9):1881–1892
Sheng Y, Wang M, Wu T et al (2019) Adaptive local learning regularized nonnegative matrix factorization for data clustering. Appl Intell 49(6):2151–2168
Sidiropoulos ND, De Lathauwer L, Fu X et al (2017) Tensor decomposition for signal processing and machine learning. IEEE Trans Signal Process 65(13):3551–3582
Sun F, Xu M, Hu X et al (2016) Graph regularized and sparse nonnegative matrix factorization with hard constraints for data representation. Neurocomputing 173:233–244
Wang C, Yan S, Zhang L et al (2009) Non-negative semi-supervised learning. In: Artificial Intelligence and Statistics, PMLR, pp 575–582
Wang C, Zhang J, Wu T et al (2022) Semi-supervised nonnegative matrix factorization with positive and negative label propagations. Appl Intell. https://doi.org/10.1007/s10489-021-02940-z
Xu W, Liu X, Gong Y (2003) Document clustering based on non-negative matrix factorization. In: Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval, pp 267–273
Xu Y (2015) Alternating proximal gradient method for sparse nonnegative Tucker decomposition. Math Program Comput 7(1):39–70
Yin W, Ma Z (2019) LE & LLE regularized nonnegative Tucker decomposition for clustering of high dimensional datasets. Neurocomputing 364:77–94
Yu N, Wu MJ, Liu JX et al (2020) Correntropy-based hypergraph regularized NMF for clustering and feature selection on multi-cancer integrated data. IEEE Trans Cybern 51(8):3952–3963
Zhang J, Han Y, Jiang J (2017) Semi-supervised tensor learning for image classification. Multimedia Syst 23(1):63–73
Zhang J, Li X, Jing P et al (2017) Low-rank regularized heterogeneous tensor decomposition for subspace clustering. IEEE Signal Process Lett 25(3):333–337
Zhao M, Li W, Li L et al (2021) Three-order tensor creation and Tucker decomposition for infrared small-target detection. IEEE Trans Geosci Remote Sens 60:1–16
Zhao YY, Jiao CN, Wang ML et al (2022) Htrpca: Hypergraph regularized tensor robust principal component analysis for sample clustering in tumor omics data. Interdiscip Sci 14(1):22–33
Zhou G, Cichocki A, Zhao Q et al (2015) Efficient nonnegative Tucker decompositions: Algorithms and uniqueness. IEEE Trans Image Process 24(12):4990–5003
Acknowledgements
Linzhang Lu is supported by the National Natural Science Foundation of China under Grant 12161020, 12061025. Qilong Liu is supported by Natural Science Foundation of Educational Commission of Guizhou Province under Grant Qian-Jiao-He KY Zi [2021]298 and Guizhou Provincial Basis Research Program (Natural Science) (QKHJC-ZK[2023]YB245).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
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.
Wenjing Jing, Linzhang Lu and Qilong Liu contributed equally to this work.
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.
About this article
Cite this article
Jing, W., Lu, L. & Liu, Q. Graph regularized discriminative nonnegative tucker decomposition for tensor data representation. Appl Intell 53, 23864–23882 (2023). https://doi.org/10.1007/s10489-023-04738-7
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-023-04738-7