Abstract
This paper introduces a scheme for semi-supervised data representation. It proposes a flexible nonlinear embedding model that imitates the principle of spectral graph convolutions. Structured data are exploited in order to determine nonlinear and linear models. The introduced scheme takes advantage of data graphs at two different levels. First, it incorporates manifold regularization that is naturally encoded by the graph itself. Second, the regression model is built on the convolved data samples that are obtained by the joint use of the data and their associated graph. The proposed semi-supervised embedding can tackle challenges related to over-fitting in image data spaces. The proposed graph convolution-based semi-supervised embedding paves the way to new theoretical and application perspectives related to the nonlinear embedding. Indeed, building flexible models that adopt convolved data samples can enhance both the data representation and the final performance of the learning system. Several experiments are conducted on six image datasets for comparing the introduced scheme with many state-of-art semi-supervised approaches. These experimental results show the effectiveness of the introduced data representation scheme.
Similar content being viewed by others
References
Belkin M, Niyogi P, Sindhwani V (2006) Manifold regularization: a geometric framework for learning from labeled and unlabeled examples. J Mach Learn Res 7:2399–2434
Belkin M, Niyogi P (2001) Laplacian eigenmaps and spectral techniques for embedding and clustering. Adv Neural Inform Process Syst 14:585–591
Cai D, He X, Han J (2007) Semi-supervised discriminant analysis. In: IEEE international conference on computer vision, pp 1–7
Dornaika F, El Traboulsi Y (2016) Learning flexible graph-based semi-supervised embedding. IEEE Trans Cybern 46(1):206–218
Dornaika F, Traboulsi YE (2017) Matrix exponential based semi-supervised discriminant embedding. Pattern Recognit 61:92–103
Dornaika F, Traboulsi YE (2019) Joint sparse graph and flexible embedding for graph-based semi-supervised learning. Neural Netw 114:91–95
Dornaika F, Kejani M, Bosaghzadeh A (2017) Graph construction using adaptive local hybrid coding scheme. Neural Netw 95:91–101
El Traboulsi Y, Dornaika F, Assoum A (2015) Kernel flexible manifold embedding for pattern classification. Neurocomputing 167:517–527
Fang X, Xu Y, Li X, Lai Z, Wong WK (2015) Learning a nonnegative sparse graph for linear regression
Franceschi L, Niepert M, Pontil M, He X (2019) Learning discrete structures for graph neural networks. In: International conference on machine learning, pp 1972–1982
Hamilton ZYW, Leskovec J (2017) Inductive representation learning on large graphs. In: Advances in neural information processing systems, pp 1024–1034
Hou C, Nie F, Li X, Yi D, Wu Y (2014) Joint embedding learning and sparse regression: a framework for unsupervised feature selection. IEEE Trans Cybern 44(6):793–804
Huang H, Liu J, Pan Y (2012) Semi-supervised marginal fisher analysis for hyperspectral image classification. ISPRS Ann Photogramm Remote Sens Spatial Inform Sci 3:377–382
Kar P, Li S, Narasimhan H, Chawla S, Sebastiani F (2016)Online optimization methods for the quantification problem. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining
Kejani MT, Dornaika F, Talebi H (2020) Graph convolution networks with manifold regularization for semi-supervised learning. Neural Netw 127:160–167
Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: International conference on learning representations
Klicpera ABJ, Gunnemann S (2019) Predict then propagate: graph neural networks meet personalized pagerank. In: International conference on learning representations
Korda N, Szorenyi, B, Li S (2016) Distributed clustering of linear bandits in peer to peer networks. In: International conference on machine learning
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105
Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: IEEE conference on computer vision and pattern recognition, pp 2169–2178
LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
Li LJ, Li FF (2007) What, where and who? Classifying events by scene and object recognition. In: IEEE international conference on computer vision, pp 1–8
Liang Y, You L, Lu X, He Z, Wang H (2018) Low-rank projection learning via graph embedding. Neurocomputing 348:97–106
Li S, Chen W, Li S, Leung K-S (2019) Improved algorithm on online clustering of bandits. arXiv:1902.09162
Li S, Karatzoglou A, Gentile C (2016) Collaborative filtering bandits. arXiv:1502.03473
Liu W, Wang J, Chang S-F (2012) Graph-based semi-supervised learning. Proc IEEE 100(9):2624–2638
Liu W, Chang S-F (2009) Robust multi-class transductive learning with graphs. In: IEEE conference on computer vision and pattern recognition, 2009. CVPR 2009, pp 381–388. IEEE
Mahadik K, Wu Q, Li S, Sabne A (2020) Fast distributed bandits for online recommendation systems
Nene SA, Nayar S, Murase H (1996) Columbia object image library (COIL-20). In: Technical report CUCS-005-96
Nie F, Xu D, Tsang IW-H, 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 Z, Wang R, Li X (2020) Submanifold-preserving discriminant analysis with an auto-optimized graph. IEEE Trans Cybern 50(8):3682–3695
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, pp 1501–1511
Nie F, Dong F, Li X (2020) Unsupervised and semisupervised projection with graph optimization. In: IEEE transactions on neural networks and learning systems
Ojala T, Pietikäinen M, Harwood D (1996) A comparative study of texture measures with classification based on featured distributions. Pattern Recognit 29(1):51–59
Qiao L, Chen S, Tan X (2010) Sparsity preserving discriminant analysis for single training image face recognition. Pattern Recognit Lett 31(5):422–429
Qu M, Bengio Y, Tang J (2019) GMNN: graph Markov neural networks. In: International conference on machine learning, pp 5241–5250
Raducanu B, Dornaika F (2012) A supervised non-linear dimensionality reduction approach for manifold learning. Pattern Recognit 45(6):2432–2444
Roweis ST, Saul LK (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500):2323–2326
Tenenbaum JB, De Silva V, Langford JC (2000) A global geometric framework for nonlinear dimensionality reduction. Science 290(5500):2319–2323
Velickovic WL H P L YB P, Fedus W, Hjelm RD (2019) Deep graph infomax. In: International conference on learning representations
Wan M, Li M, Yang G, Gai S, Jin Z (2014) Feature extraction using two-dimensional maximum embedding difference. Inf Sci 274:55–69
Wan M, Lai Z, Yang G, Yang Z, Zhang F, Zheng H (2017) Local graph embedding based on maximum margin criterion via fuzzy set. Fuzzy Sets Syst 318:120–131
Wang F, Wang X, Zhang D, Zhang C, Li T (2009) Marginface: a novel face recognition method by average neighborhood margin maximization. Pattern Recognit 42(11):2863–2875
Wang H, Leskovec J (2020) Unifying graph convolutional neural networks and label propagation. arXiv preprint arXiv:2002.06755
Wen J, Xu Y, Liu H (2020) Incomplete multiview spectral clustering with adaptive graph learning. IEEE Trans Cybern 50(4):1418–1429
Wu H, Prasad S (2018) Semi-supervised dimensionality reduction of hyperspectral imagery using pseudo-labels. Pattern Recognit 74:212–224
Wu F, Souza A, Zhang T, Fifty C, Yu T, Weinberger K (2019) Simplifying graph convolutional networks. In: International conference on machine learning, pp 6861–6871
Yan S, Xu D, Zhang B, Zhang H, Yang Q, Lin S (2007) Graph embedding and extensions: a general framework for dimensionality reduction. IEEE Trans Pattern Anal Mach Intell 29(1):40–51
Yu G, Zhang G, Domeniconi C, Yu Z, You J (2012) Semi-supervised classification based on random subspace dimensionality reduction. Pattern Recognit 45(3):1119–1135
Yuan Y, Mou L, Lu X (2015) Scene recognition by manifold regularized deep learning architecture. IEEE Trans Neural Netw Learn Syst 26(10):2222–2233
Zhang Z, Jia L, Zhao M, Ye Q, Zhang M, Wang M (2018) Adaptive non-negative projective semi-supervised learning for inductive classification. Neural Netw 108:128–145
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
Zhu R, Dornaika F, Ruichek Y (2019) Joint graph based embedding and feature weighting for image classification. Pattern Recognit 93:458–469
Zhu R, Dornaika F, Ruichek Y (2019) Learning a discriminant graph-based embedding with feature selection for image categorization. Neural Netw 111:35–46
Zhu R, Dornaika F, Ruichek Y (2020) Semi-supervised elastic manifold embedding with deep learning architecture. Pattern Recognit 107:107425
Zhu X, Ghahramani Z, Lafferty J et al (2003) Semi-supervised learning using Gaussian fields and harmonic functions, vol 3, pp 912–919
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.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Dornaika, F. Flexible data representation with graph convolution for semi-supervised learning. Neural Comput & Applic 33, 6851–6863 (2021). https://doi.org/10.1007/s00521-020-05462-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-020-05462-w