Geodesic Distance Function Learning via Heat Flow on Vector Fields

Learning a distance function or metric on a given data manifold is of great importance in machine learning and pattern recognition. Many of the previous works first embed the manifold to Euclidean space and then learn the distance function. However, such a scheme might not faithfully preserve the distance function if the original manifold is not Euclidean. Note that the distance function on a manifold can always be well-defined. In this paper, we propose to learn the distance function directly on the manifold without embedding. We first provide a theoretical characterization of the distance function by its gradient field. Based on our theoretical analysis, we propose to first learn the gradient field of the distance function and then learn the distance function itself. Specifically, we set the gradient field of a local distance function as an initial vector field. Then we transport it to the whole manifold via heat flow on vector fields. Finally, the geodesic distance function can be obtained by requiring its gradient field to be close to the normalized vector field. Experimental results on both synthetic and real data demonstrate the effectiveness of our proposed algorithm.

[1]  A. Mennucci,et al.  Hamilton—Jacobi Equations and Distance Functions on Riemannian Manifolds , 2002, math/0201296.

[2]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[3]  Stéphane Lafon,et al.  Diffusion maps , 2006 .

[4]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.

[5]  A. Defant,et al.  Tensor Norms and Operator Ideals , 2011 .

[6]  Mikhail Belkin,et al.  Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering , 2001, NIPS.

[7]  Jürgen Jost,et al.  Riemannian Geometry and Geometric Analysis, 5th Edition , 2008 .

[8]  I. Holopainen Riemannian Geometry , 1927, Nature.

[9]  Rong Jin,et al.  Regularized Distance Metric Learning: Theory and Algorithm , 2009, NIPS.

[10]  Jiawei Han,et al.  Parallel Field Ranking , 2012, TKDD.

[11]  U. Feige,et al.  Spectral Graph Theory , 2015 .

[12]  R. Abraham,et al.  Manifolds, tensor analysis, and applications: 2nd edition , 1988 .

[13]  A. Singer,et al.  Vector diffusion maps and the connection Laplacian , 2011, Communications on pure and applied mathematics.

[14]  Terence Sim,et al.  The CMU Pose, Illumination, and Expression Database , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Keenan Crane,et al.  Geodesics in heat: A new approach to computing distance based on heat flow , 2012, TOGS.

[16]  B. Nadler,et al.  Diffusion maps, spectral clustering and reaction coordinates of dynamical systems , 2005, math/0503445.

[17]  Kilian Q. Weinberger,et al.  Learning a kernel matrix for nonlinear dimensionality reduction , 2004, ICML.

[18]  Michael I. Jordan,et al.  Distance Metric Learning with Application to Clustering with Side-Information , 2002, NIPS.

[19]  Xiaofei He,et al.  Semi-supervised Regression via Parallel Field Regularization , 2011, NIPS.

[20]  Gert R. G. Lanckriet,et al.  Metric Learning to Rank , 2010, ICML.

[21]  F. Mémoli,et al.  Fast computation of weighted distance functions and geodesics on implicit hyper-surfaces: 730 , 2001 .

[22]  D. Donoho,et al.  Hessian eigenmaps: Locally linear embedding techniques for high-dimensional data , 2003, Proceedings of the National Academy of Sciences of the United States of America.

[23]  Xiaofei He,et al.  Parallel vector field embedding , 2013, J. Mach. Learn. Res..

[24]  John M. Lee Introduction to Smooth Manifolds , 2002 .

[25]  Christopher D. Manning,et al.  Introduction to Information Retrieval , 2010, J. Assoc. Inf. Sci. Technol..

[26]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[27]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[28]  Bernhard Schölkopf,et al.  Ranking on Data Manifolds , 2003, NIPS.

[29]  J. Jost Riemannian geometry and geometric analysis , 1995 .

[30]  Michèle Vergne,et al.  Heat Kernels and Dirac Operators: Grundlehren 298 , 1992 .