Continuous-Flow Graph Transportation Distances

Optimal transportation distances are valuable for comparing and analyzing probability distributions, but larger-scale computational techniques for the theoretically favorable quadratic case are limited to smooth domains or regularized approximations. Motivated by fluid flow-based transportation on $\mathbb{R}^n$, however, this paper introduces an alternative definition of optimal transportation between distributions over graph vertices. This new distance still satisfies the triangle inequality but has better scaling and a connection to continuous theories of transportation. It is constructed by adapting a Riemannian structure over probability distributions to the graph case, providing transportation distances as shortest-paths in probability space. After defining and analyzing theoretical properties of our new distance, we provide a time discretization as well as experiments verifying its effectiveness.

[1]  Ahmed I. Zayed,et al.  Wavelets and multiscale analysis : theory and applications , 2011 .

[2]  Fan Chung,et al.  Spectral Graph Theory , 1996 .

[3]  Emilio Frazzoli,et al.  An Explicit Formulation of the Earth Movers Distance with Continuous Road Map Distances , 2013, 1309.7098.

[4]  G. Burton TOPICS IN OPTIMAL TRANSPORTATION (Graduate Studies in Mathematics 58) By CÉDRIC VILLANI: 370 pp., US$59.00, ISBN 0-8218-3312-X (American Mathematical Society, Providence, RI, 2003) , 2004 .

[5]  Julien Rabin,et al.  Wasserstein Barycenter and Its Application to Texture Mixing , 2011, SSVM.

[6]  Leonidas J. Guibas,et al.  Dirichlet Energy for Analysis and Synthesis of Soft Maps , 2013 .

[7]  Mehran Mesbahi,et al.  Advection on graphs , 2011, IEEE Conference on Decision and Control and European Control Conference.

[8]  J. Lott Some Geometric Calculations on Wasserstein Space , 2006, math/0612562.

[9]  F. L. Hitchcock The Distribution of a Product from Several Sources to Numerous Localities , 1941 .

[10]  Gabriel Peyré,et al.  Optimal Transport with Proximal Splitting , 2013, SIAM J. Imaging Sci..

[11]  Daniel Cremers,et al.  The wave kernel signature: A quantum mechanical approach to shape analysis , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[12]  Andrew McGregor,et al.  Sketching Earth-Mover Distance on Graph Metrics , 2013, APPROX-RANDOM.

[13]  R. McCann A Convexity Principle for Interacting Gases , 1997 .

[14]  Julien Rabin,et al.  Sliced and Radon Wasserstein Barycenters of Measures , 2014, Journal of Mathematical Imaging and Vision.

[15]  Marco Cuturi,et al.  Sinkhorn Distances: Lightspeed Computation of Optimal Transportation , 2013, NIPS 2013.

[16]  Michael Lindenbaum,et al.  Nonnegative Matrix Factorization with Earth Mover's Distance Metric for Image Analysis , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Björn Ommer,et al.  Efficient Clustering Earth Mover's Distance , 2010, ACCV.

[18]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[19]  Pascal Frossard,et al.  The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains , 2012, IEEE Signal Processing Magazine.

[20]  Stephen P. Boyd,et al.  Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..

[21]  Yann Brenier,et al.  A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem , 2000, Numerische Mathematik.

[22]  C. Villani Topics in Optimal Transportation , 2003 .

[23]  Giovanni Soda,et al.  Using Earth Mover's Distance in the Bag-of-Visual-Words Model for Mathematical Symbol Retrieval , 2011, 2011 International Conference on Document Analysis and Recognition.

[24]  Arnaud Doucet,et al.  Fast Computation of Wasserstein Barycenters , 2013, ICML.

[25]  Leonidas J. Guibas,et al.  Wasserstein Propagation for Semi-Supervised Learning , 2014, ICML.

[26]  Chong-Wah Ngo,et al.  Ontology-based visual word matching for near-duplicate retrieval , 2008, 2008 IEEE International Conference on Multimedia and Expo.

[27]  Yuan Yao,et al.  Statistical ranking and combinatorial Hodge theory , 2008, Math. Program..

[28]  Julien Rabin,et al.  Geodesic Shape Retrieval via Optimal Mass Transport , 2010, ECCV.

[29]  Daniela Giorgi,et al.  SHape REtrieval Contest 2007: Watertight Models Track , 2007 .

[30]  Alexei A. Efros,et al.  Discovering objects and their location in images , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[31]  Leonidas J. Guibas,et al.  The Earth Mover's Distance as a Metric for Image Retrieval , 2000, International Journal of Computer Vision.

[32]  C. Udriste,et al.  Convex Functions and Optimization Methods on Riemannian Manifolds , 1994 .

[33]  Stephen P. Boyd,et al.  Graph Implementations for Nonsmooth Convex Programs , 2008, Recent Advances in Learning and Control.