Abstract
In recent years, a series of manifold learning algorithms have been proposed for nonlinear dimensionality reduction. Most of them can run in a batch mode for a set of given data points, but lack a mechanism to deal with new data points. Here we propose an extension approach, i.e., mapping new data points into the previously learned manifold. The core idea of our approach is to propagate the known coordinates to each of the new data points. We first formulate this task as a quadratic programming, and then develop an iterative algorithm for coordinate propagation. Tangent space projection and smooth splines are used to yield an initial coordinate for each new data point, according to their local geometrical relations. Experimental results and applications to camera direction estimation and face pose estimation illustrate the validity of our approach.
Similar content being viewed by others
References
Baldi P, Hornik K (1989) Neural networks and principal component analysis: learning from examples without local minima. Neural Netw 2(1): 53–58
Belkin M, Niyogi P (2003) Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput 15(6): 1373–1396
Bengio Y, Paiement JF, Vincent P (2004) Out-of-sample extensions for lle, isomap, mds, eigenmaps and spectral clustering. In: Advances in neural information processing systems, p 16
Bishop CM, Svensn M, Williams CKI (1998) Gtm: the generative topographic mapping. Neural Comput 10(1): 215–234
Boyd S, Vandenberghe L (2004) Convex optimization. Cambriage University Press, Cambridge
Brand M (2003) Charting a manifold. In: Advances in neural information processing systems, vol 15. MIT Press, Cambridge, pp 961–968
Brun A, Park HJ, Kuntsson H, Westin CF (2003) Coloring of dt-mri fiber traces using laplacian eigenmaps. In: Proceedings of international conference on computer aided systems theory, Las Palmas, Spain, pp 518–529
Cai C, He XF, Han JW (2007) Efficient kernel discriminant analysis via spectral regression, Technical Report UIUCDCS-R-2007-2888, Department of Computer Science, University of Illinois at Urbana-Champaign
Carreira-Perpiñán MÁ, Lu ZD (2007) The laplacian eigenmaps latent variable models. In: International conference on artificial intelligence and statistics, San Juan, Puerto Rico
Chang H, Yeung D, Xiong Y (2004) Super-resolution through neighbor embedding. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, Washington, DC, USA, pp 275–282
Dollar P, Rabaud V, Belongie S (2007) Learning to traverse image manifolds. In: Advances in neural information processing systems, p 19
Donoho DL, Grimes C (2003) Hessian eigenmaps: locally linear embedding techniques for highdimensional data. Proc Natl Acad Arts Sci 100(10): 5591–5596
Duchon J (1977) Splines minimizing rotation-invariant semi-norms in sobolev spaces. In: Dold A, Eckmann B (eds) Constructive theory of functions of several variables. Springer, Heidelberg, pp 85–100
Golub GH, van Loan CF (1996) Matrix computations. The Johns Hopkins University Press, Maryland
Gong H, Pan C, Yang Q, Lu H, Ma S (2005) A semi-supervised framework for mapping data to the intrinsic manifold. In: Proceedings of international conference on computer vision, Beijing, China, pp 98–105
Gorban A, Kegl B, Wunsch D, Zinovyev A (2007) Principal manifolds for data visualization and dimension reduction. Springer, Berlin
Gourier N, Hall D, Crowley J (2004) Estimating face orientation from robust detection of salient facial features. In: ICPR workshop on visual observation of deictic gestures
Hadid A, Kouropteva O, Pietikainen M (2002) Unsupervised learning using locally linear embedding: experiments in face pose analysis. In: International conference of pattern recognition, vol 1, Quebec, Canada, pp 111–114
Ham J, Lee DD, Saul LK (2004) Semisupervised alignment of manifolds. In: International workshop on artificial intelligence and statistics Barbados, West Indies, pp 120–127
Hastie T, Stuetzle W (1989) Principal curves. J Am Stat Assoc 84(406): 502–516
He XF, Niyogi P (2003) Locality preserving projections. In: NIPS, Vancouver, Canada
Hein M, Maier M (2007) Manifold denosing. In: Advances in neural information processing systems, vol 19. MIT Press, Cambridge, pp 1–8
Jenkins OC, Mataric MJ (2004) A spatio-temporal extension to isomap nonlinear dimension reduction. In: ‘ICML’, Banff, Alberta, Canada, pp 441–448
Jolliffe IT (1986) Principal component analysis. Springer, New York
Kalousis A, Prados J, Hilario M (2007) Stability of feature selection algorithms: a study on high-dimensional spaces. Knowl Inf Syst 12(1): 95–116
Kegl B, Krzyzak A, Linder T, Zeger K (2000) Learning and design of principal curves. IEEE Trans Pattern Anal Mach Intell 22(3): 281–297
Kohonen T (2001) Self-organization maps, 3rd edn. Springer, Berlin
Kouropteva O, Okun O, Pietikäinen M (2005) Incremental locally linear embedding. Pattern Recogn 38(10): 1764–1767
Law M, Jain AK (2006) Incremental nonlinear dimensionality reduction by manifold learning. IEEE Trans Pattern Anal Mach Intell 28(3): 377–391
Lei H, Govindaraju V (2007) Generalized regression model for sequence matching and clustering. Knowl Inf Syst 12(1): 77–94
Mao J, Jain AK (1995) Artificial neural networks for feature extraction and multivariate data projection. IEEE Trans Neural Netw 16(2): 296–317
Min W, Lu K, He X (2004) Locality pursuit embedding. Pattern Recogn 37(4): 781–788
Mosci S, Rosasco L, Verri A (2007) Dimensionality reduction and generalization. In: Proceedings of international conference on machine learning, Corvallis, OR, USA, pp 657–664
Nene S, Nayar S, Murase H (1996) Columbia object image library (coil-20), Technical report, Columbia University
Niskanen M, Silven O (2003) Comparison of dimensionality reduction methods for wood surface inspection. In: Proceedings of international conference on quality control by artificial vision, Gatlinbura, Tennessee, USA, pp 178–188
Qiu G, Guan J (2005) Color by linear neighborhood embedding. In: IEEE international conference on image processing, Genoa, Italy, pp 988–991
Rosset S, Perlich C, Zadrozny B (2007) Ranking-based evaluation of regression models. Knowl Inf Syst 12(3): 331–353
Roweis S, Saul L (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290(1): 2323–2326
Sammom JW (1969) A nonlinear mapping for data structure analysis. IEEE Trans Comp 18(5): 401–409
Schoelkopf B, Smola AJ, Muller KR (1998) Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput 10(5): 1299–1319
Sha F, Saul LK (2005) Analysis and extension of spectral methods for nonlinear dimensionality reduction. In: Proceedings of international conference on machine learning, Bonn, Germany, pp 784–791
Smola AJ, Mika S, Schoelkopf B, Williamson RC (2001) Regularized principal manifolds. J Mach Learn 1(3): 179–209
Tenenbaum JB, de Silva V, Langford JC (2000) A global geometric framework for nonlinear dimensionality reduction. Science 290(1): 2319–2323
Tibshirani R (1992) Principal curves revisited. Stat Comput 2: 183–190
Vlachos M, Domeniconi C, Gunopulos D (2002) Non-linear dimensionality reduction techniques for classification and visualization. In: International conference on knowledge discovery and data mining, Edmonton, Canada, pp 645–651
Wahba G (1990) Spline models for observational data. SIAM Press, Philadelphia
Weinberger KQ, Sha F, Saul LK (2004) Learning a kernel matrix for nonlinear dimensionality reduction, In: Proceedings of international conference on machine learning, Banff, Canada, pp 888–905
Wu X, Kumar V, Quinlan R, Quinlan JR, Ghosh J, Yang Q, Motoda H, McLachlan GJ, Ng A, Liu B, Yu PS, Zhou Z-H, Steinbach M, Hand DJ, Steinberg D (2008) Top 10 algorithms in data mining. Knowl Inf Syst 14(1): 1–37
Xiang SM, Nie FP, Zhang CS, Zhang CX (2006) Spline embedding for nonlinear dimensionality reduction. In: European conference on machine learning, Berlin, Germany, pp 825–832
Yan S, Xu D, Zhang B, Zhang H (2005) Graph embedding: a general framework for dimensionality reduction. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, San Diego, CA, USA, pp 830–837
Yang M-H (2002) Face recognition using extended isomap. In: Proceedings of IEEE international conference on image processing, Singapore, pp 117–120
Yang X, Fu H, Zha H, Barlow J (2006) Semi-supervised nonlinear dimensionality reduction. In: International conference on machine learning, Pittsburgh, USA, pp 1065–1072
Yoon J (2001) Spectral approximation orders of radial basis function interpolation on the sobolev space. SIAM J Math Anal 33(4): 946–958
Zhang Z, Zha H (2004) Principal manifolds and nonlinear dimensionality reduction via tangent space alignment. SIAM J Sci Comput 26(1): 313–338
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Xiang, S., Nie, F., Song, Y. et al. Embedding new data points for manifold learning via coordinate propagation. Knowl Inf Syst 19, 159–184 (2009). https://doi.org/10.1007/s10115-008-0161-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10115-008-0161-3