Abstract
Graph-based learning methods are very useful for many machine learning approaches and classification tasks. Constructing an informative graph is one of the most important steps since a graph can significantly affect the final performance of the learning algorithms. Sparse representation is a useful tool in machine learning and pattern recognition area. Recently, it was shown that sparse graphs (sparse representation based graphs) provide a powerful approach to graph-based semi-supervised classification. In this paper, we introduce a new graph construction method that simultaneously provides a sparse graph and integrates manifold constraints on the sparse coefficients without any prior knowledge on the graph or on its similarity matrix. Furthermore, we propose an efficient solution to the optimization problem. The proposed method imposes that the sparse coding vectors of similar samples should be also similar. Different from existing graph construction methods that are based on the use of explicit constraints or a predefined graph matrix, the proposed smoothness constraints on the graph weights implicitly adapt data to the global structure of the estimated graph. A series of experiments conducted on several public image databases shows that the proposed method can outperform many state-of-the-art methods when applied to the problem of graph-based label propagation.
Similar content being viewed by others
Notes
Degree means the number of the edges connected to the node.
References
Qian P, Chung F, Wang S, Deng Z (2012) Fast graph-based relaxed clustering for large data sets using minimal enclosing ball. Syst Man Cybern Part B Cybern IEEE Trans 42(3):672–687
Dornaika F, Bosaghzadeh A, Raducanu B (2013) Efficient graph construction for label propagation based multi-observation face recognition. Int Workshop Hum Behavior Underst vol LNCS 8212:124–135
Wang J, Lu C, Wang M, Li P, Yan S, Hu X (2014) Robust face recognition via adaptive sparse representation. Cybern IEEE Trans 44(12):2368–2378
Nie F, Wang X, Huang H (2014) Clustering and projected clustering with adaptive neighbors. In: ACM SIGKDD international conference on knowledge discovery and data mining
Zhang L, Gao Y, Hong C, Feng Y, Zhu J, Cai D (2014) Feature correlation hypergraph: exploiting high-order potentials for multimodal recognition. Cybern IEEE Trans 44(8):1408–1419
Xuan J, Lu J, Zhang G, Luo X (2015) Topic model for graph mining. IEEE Trans Cybern 45(12):2792–2803
Zhou D, Huang J, Schölkopf B (2005) Learning from labeled and unlabeled data on a directed graph. In: Proceedings of the 22nd international conference on Machine learning, ACM, pp 1036–1043
Jebara T, Wang J, Chang S-F (2009) Graph construction and b-matching for semi-supervised learning. In: Proceedings of the 26th annual international conference on machine learning, ACM, pp 441–448
Wang J, Wang F, Zhang C, Shen HC, Quan Long (2009) Linear neighborhood propagation and its applications. IEEE Trans Pattern Anal Mach Intell 31(9):1600–1615
Wei J, Peng H (2008) Neighbourhood preserving based semi-supervised dimensionality reduction. Electron Lett 44(20):1190–1192
Wright J, Yang AY, Ganesh A, Sastry SS, Ma Y (2009) Robust face recognition via sparse representation. IEEE Trans Pattern Anal Mach Intell 31(2):210–227
Qiao L, Chen S, Tan X (2010) Sparsity preserving projections with applications to face recognition. Pattern Recogn 43(1):331–341
Tang J, Shao L, Li X, Lu K (2015) A local structural descriptor for image matching via normalized graph laplacian embedding. Cybern IEEE Trans 46(2):410–420
Iosifidis A, Tefas A, Pitas I (2015) Graph embedded extreme learning machine. Cybern IEEE Trans 46(1):311–324
Carneiro MG, Cupertino TH, Cheng R, Jin Y, Zhao L (2017) Nature-inspired graph optimization for dimensionality reduction. In: Interantionl conference on tools with artificial intelligence
Dornaika F, El Traboulsi Y (2019) Joint sparse graph and flexible embedding for graph-based semi-supervised learning. Neural Netw 114:91–95
Wang M, Fu W, Hao S, Tao D, Wu X (2016) Scalable semi-supervised learning by efficient anchor graph regularization. IEEE Trans Knowl Data Eng 28(7):1864–1877
Wang R, Nie F, Yu W (2017) Fast spectral clustering with anchor graph for large hyperspectral images. IEEE Geosci Remote Sens Lett 14(11):2003–2007
Belkin M, Niyogi P (2003) Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput 15(6):1373–1396
de Sousa CAR, Rezende SO, Batista GEAPA (2013) Influence of graph construction on semi-supervised learning. In: Machine learning and knowledge discovery in databases, Springer, pp 160–175
Daitch SI, Kelner JA, Spielman DA (2009) Fitting a graph to vector data. In: International conference on machine learning, pp 201–208
Roweis S, Saul L (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500):2323–2326
Yan S, Wang H (2009) Semi-supervised learning by sparse representation. In: SIAM international conference on data mining, SIAM, pp 792–801
Cheng B, Yang J, Yan S, Yun F, Huang TS (2010) Learning with l1 graph for image analysis. IEEE Trans Image Process 19(4):858–866
Wang C, Yan S, Zhang L, Zhang H-J (2009) Multi-label sparse coding for automatic image annotation. In: IEEE conference on computer vision and pattern recognition, IEEE, pp 1643–1650
He X, Ji M, Bao H (2009) Graph embedding with constraints. Int Jt Conf Artif Intell 9:1065–1070
Abernethy J, Chapelle O, Castillo C (2008) Web spam identification through content and hyperlinks. In: Proceedings of the 4th international workshop on Adversarial information retrieval on the web, ACM, pp 41–44
Zhang T, Popescul A, Dom B (2006) Linear prediction models with graph regularization for web-page categorization. In: Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining, ACM, pp 821–826
Gao S, Tsang IW, Chia L-T, Zhao P (2010) Local features are not lonely–laplacian sparse coding for image classification. In: IEEE conference on computer vision and pattern recognition, IEEE, pp 3555–3561
Gao S, Tsang IW-H, Chia L-T (2013) Laplacian sparse coding, hypergraph laplacian sparse coding, and applications. IEEE Trans Pattern Anal Mach Intell 35(1):92–104
Chen S-B, Ding CHQ, Luo B (2014) Similarity learning of manifold data. IEEE Trans Cybern 99:1–13
Nie F, Wang X, Jordan MI, Huang H (2016) The constrained laplacian rank algorithm for graph-based clustering. In: association for the advancement of artificial intelligence
Nie F, Wang H, Huang H, Ding CHQ (2011) Unsupervised and semi-supervised learning via l1-norm graph. In: IEEE international conference on computer vision, ICCV 2011
Zhou G, Lu Z, Peng Y (2013) L1-graph construction using structured sparsity. Neurocomputing 120:441–452
Weng L, Dornaika F, Jin Z (2016) Graph construction based on data self-representativeness and laplacian smoothness. Neurocomputing 60(207):813–823
Zhu X, Ghahramani Z, Lafferty J et al (2003) Semi-supervised learning using gaussian fields and harmonic functions. Int Conf Mach Learn 3:912–919
Zhou D, Bousquet O, Lal TN, Weston J, Schölkopf B (2004) Learning with local and global consistency. Adv Neural Inf Process Syst 16:321–328
Belkin Mikhail, Niyogi Partha, Sindhwani Vikas (2006) Manifold regularization: a geometric framework for learning from labeled and unlabeled examples. J Mach Learn Res 7:2399–2434
Liu W, Chang S-F (2009) Robust multi-class transductive learning with graphs. In: IEEE conference on computer vision and pattern recognition, IEEE, pp 381–388
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
Takala V, Ahonen T, Pietikainen M (2005) Block-based methods for image retrieval using local binary patterns. In: Image analysis, SCIA, volume LNCS, p 3540
Ahonen T, Hadid A, Pietikainen M (2006) Face description with local binary patterns: application to face recognition. IEEE Trans Pattern Anal Mach Intell 28(12):2037–2041
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 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. Sparse graphs using global and local smoothness constraints. Int. J. Mach. Learn. & Cyber. 11, 1241–1251 (2020). https://doi.org/10.1007/s13042-019-01035-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-019-01035-z