Abstract
Recently, graph-based semi-supervised learning (GSSL) has received much attention. On the other hand, less attention has been paid to the problem of large-scale GSSL for inductive multi-class classification. Existing scalable GSSL methods rely on a hard linear constraint. They cannot predict the labelling of test samples, or use predefined graphs, which limits their applications and performance. In this paper, we propose an inductive algorithm that can handle large databases by using anchors. The main contribution compared to existing scalable semi-supervised models is the integration of the anchor graph computation into the learned model. We develop a criterion to jointly estimate the unlabeled sample labels, the mapping of the feature space to the label space, and the affinity matrix of the anchor graph. Furthermore, the fusion of labels and features of anchors is used to construct the graph. Using the projection matrix, it can also predict the labels of the test samples by linear transformation. Experimental results on the large datasets NORB, RCV1 and Covtype show the effectiveness, scalability and superiority of the proposed method. The code of the proposed method can be found at the following link https://github.com/ZoulfikarIB/SGRFME .
Similar content being viewed by others
Data availability
The data that support the findings of this study are available upon reasonable request.
References
An L, Chen X, Yang S (2017) Multi-graph feature level fusion for person re-identification. Neurocomputing 259:39–45
An J, Zhao X, Shi M, Liu X, Guo J (2021) Joint neighborhood preserving and projected clustering for feature extraction. Neurocomputing 488:572–580
Belkin M, Niyogi P, Sindhwani V (2006) Manifold regularization: a geometric framework for learning from labeled and unlabeled examples. J Mach Learn Res 7(85):2399–2434
Chen H-T, Chang H-W, Liu T-L (2005) Local discriminant embedding and its variants. In: 2005 IEEE Computer Society conference on computer vision and pattern recognition (CVPR’05), 2005, vol 2, pp 846–853
Collobert R, Sinz F, Weston J, Bottou L (2006) Large scale transductive SVMs. J Mach Learn Res 7(08):1687–1712
Cui B, Xie X, Hao S, Cui J, Lu Y (2018) Semi-supervised classification of hyperspectral images based on extended label propagation and rolling guidance filtering. Remote Sens 10(4):515
de Sousa CAR (2016) An inductive semi-supervised learning approach for the local and global consistency algorithm. In: 2016 International joint conference on neural networks (IJCNN), 2016, pp 4017–4024
Deng J, Yu J-G (2021) A simple graph-based semi-supervised learning approach for imbalanced classification. Pattern Recognit 118:108026
Dornaika F, Traboulsi YE, Assoum A (2016) Inductive and flexible feature extraction for semi-supervised pattern categorization. Pattern Recognit 60:275–285
Dornaika F, Dahbi R, Bosaghzadeh A, Ruichek Y (2017) Efficient dynamic graph construction for inductive semi-supervised learning. Neural Netw 94:192–203
Dornaika F, Baradaaji A, El Traboulsi Y (2021) Joint label inference and discriminant embedding. IEEE Trans Neural Netw Learn Syst 33(9):4413–4423
Dornaika F, Baradaaji A, El Traboulsi Y (2021) Semi-supervised classification via simultaneous label and discriminant embedding estimation. Inf Sci 546:146–165
Hamilton W, Ying Z, Leskovec J (2017) Inductive representation learning on large graphs. In: Guyon I, Luxburg UV, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R (eds) Advances in neural information processing systems, vol 30. Curran Associates, Inc., Red Hook
He Z, Xia K, Li T, Zu B, Yin Z, Zhang J (2021) A constrained graph-based semi-supervised algorithm combined with particle cooperation and competition for hyperspectral image classification. Remote Sens 13(2):193
Jia J, Ruan Q, Jin Y, An G, Ge S (2020) View-specific subspace learning and re-ranking for semi-supervised person re-identification. Pattern Recognit 108:107568
Jian M, Jung C (2021) Semi-supervised kernel matrix learning using adaptive constraint-based seed propagation. Pattern Recognit 112:107750
Kang Z, Peng C, Cheng Q, Liu X, Peng X, Xu Z, Tian L (2021) Structured graph learning for clustering and semi-supervised classification. Pattern Recognit 110:107627
Kang Z, Peng C, Cheng Q, Liu X, Peng X, Xu Z, Tian L (2021) Structured graph learning for clustering and semi-supervised classification. Pattern Recognit 110:107627
Kim K-H, Choi S (2014) Label propagation through minimax paths for scalable semi-supervised learning. Pattern Recognit Lett 45:17–25
Liu W, He J, Chang S-F (2010) Large graph construction for scalable semi-supervised learning. In: Proceedings of the 27th international conference on international conference on machine learning, ICML’10, 2010. Omnipress, Madison, pp 679–686
Liu Y, Shi H, Du H, Zhu R, Wang J, Zheng L, Mei T (2022) Boosting semi-supervised face recognition with noise robustness. IEEE Trans Circuits Syst Video Technol 32(2):778–787
Long Y, Li Y, Wei S, Zhang Q, Yang C (2019) Large-scale semi-supervised training in deep learning acoustic model for ASR. IEEE Access 7:133615–133627
Nie F, Xu D, Tsang IW, Zhang C (2010) Flexible manifold embedding: a framework for semi-supervised and unsupervised dimension reduction. IEEE Trans Image Process 19(7):1921–1932
Nie F, Wang X, Jordan IM, Huang H (2016) The constrained Laplacian rank algorithm for graph-based clustering. In: AAAI conference on artificial intelligence, 2016
Nie F, Cai G, Li X (2017) Multi-view clustering and semi-supervised classification with adaptive neighbours. In: Thirty-first AAAI conference on artificial intelligence, 2017
Qiu S, Nie F, Xu X, Qing C, Xu D (2019) Accelerating flexible manifold embedding for scalable semi-supervised learning. IEEE Trans Circuits Syst Video Technol 29(9):2786–2795
Roweis ST, Saul LK (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500):2323–2326
Sindhwani V, Niyogi P (2005) Linear manifold regularization for large scale semi-supervised learning. In: Proceedings of the 22nd ICML workshop on learning with partially classified training data, 2005
Sindhwani V, Niyogi P, Belkin M, Keerthi S (2005) Linear manifold regularization for large scale semi-supervised learning. In: Proceedings of the 22nd ICML workshop on learning with partially classified training data, 2005, vol 1
Song Z, Yang X, Xu Z, King I (2021) Graph-based semi-supervised learning: a comprehensive review. CoRR, abs/2102.13303
Tu E, Wang Z, Yang J, Kasabov N (2022) Deep semi-supervised learning via dynamic anchor graph embedding in latent space. Neural Netw 146:350–360
Wang M, Fu W, Hao S, Tao D, Wu X (2016a) Scalable semi-supervised learning by efficient anchor graph regularization. IEEE Trans Knowl Data Eng 28(7):1864–1877
Wang M, Fu W, Hao S, Tao D, Wu X (2016b) Scalable semi-supervised learning by efficient anchor graph regularization. IEEE Trans Knowl Data Eng 28(7):1864–1877
Wang F, Zhu L, Xie L, Zhang Z, Zhong M (2021) Label propagation with structured graph learning for semi-supervised dimension reduction. Knowl Based Syst 225:107130
Wang Z, Zhang L, Wang R, Nie F, Li X (2022) Semi-supervised learning via bipartite graph construction with adaptive neighbors. IEEE Trans Knowl Data Eng. https://doi.org/10.1109/TKDE.2022.3151315
Wu G, Li Y, Xi J, Yang X, Liu X (2012) Local learning integrating global structure for large scale semi-supervised classification. In: 2012 8th International conference on natural computation, 2012, pp 1044–1049
Wu X, Zhao L, Akoglu L (2019) A quest for structure: jointly learning the graph structure and semi-supervised classification
Yang S, Ienco D, Esposito R, Pensa RG (2021) ESA: a generic framework for semi-supervised inductive learning. Neurocomputing 447:102–117
Yi Y, Chen Y, Wang J, Lei G, Dai J, Zhang H (2020) Joint feature representation and classification via adaptive graph semi-supervised nonnegative matrix factorization. Signal Process Image Commun 89:115984
Yuan Y, Li X, Wang Q, Nie F (2021) A semi-supervised learning algorithm via adaptive Laplacian graph. Neurocomputing 426:162–173
Zaman SMK, Liang X (2021) An effective induction motor fault diagnosis approach using graph-based semi-supervised learning. IEEE Access 9:7471–7482
Zhan W, Zhang M-L (2017) Inductive semi-supervised multi-label learning with co-training. In: Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, KDD ’17, 2017. Association for Computing Machinery, New York, pp 1305–1314
Zhang Y-M, Huang K, Geng G-G, Liu C-L (2015) MTC: a fast and robust graph-based transductive learning method. IEEE Trans Neural Netw Learn Syst 26(9):1979–1991
Zhang Z, Li F, Jia L, Qin J, Zhang L, Yan S (2018) Robust adaptive embedded label propagation with weight learning for inductive classification. IEEE Trans Neural Netw Learn Syst 29(8):3388–3403
Zhang Z, Zhang Y, Liu G, Tang J, Yan S, Wang M (2019) Joint label prediction based semi-supervised adaptive concept factorization for robust data representation. IEEE Trans Knowl Data Eng 32(5):952–970
Zhao M, Zhang Y, Zhang Z, Liu J, Kong W (2019) ALG: adaptive low-rank graph regularization for scalable semi-supervised and unsupervised learning. Neurocomputing 370:16–27
Zhou D, Bousquet O, Lal TN, Weston J, Schölkopf B (2004) Learning with local and global consistency. In: Thrun S, Saul LK, Schölkopf B (eds) Advances in neural information processing systems, vol 16. MIT Press, Cambridge, pp 321–328
Zhu X, Lafferty J (2005) Harmonic mixtures: combining mixture models and graph-based methods for inductive and scalable semi-supervised learning, vol 1, pp 1052–1059
Zhu X, Ghahramani Z, Lafferty J (2003) Semi-supervised learning using Gaussian fields and harmonic functions. Int Conf Mach Learn 3(01):912–919
Zhu R, Dornaika F, Ruichek Y (2021) Inductive semi-supervised learning with graph convolution based regression. Neurocomputing 434:315–322
Ziraki N, Dornaika F, Bosaghzadeh A (2022) Multiple-view flexible semi-supervised classification through consistent graph construction and label propagation. Neural Netw 146:174–180
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Ethical approval
This article complies with ethical standards.
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.
About this article
Cite this article
Ibrahim, Z., Bosaghzadeh, A. & Dornaika, F. Joint graph and reduced flexible manifold embedding for scalable semi-supervised learning. Artif Intell Rev 56, 9471–9495 (2023). https://doi.org/10.1007/s10462-023-10397-4
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10462-023-10397-4