The mutual information between graphs
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10045/68546
Title: | The mutual information between graphs |
---|---|
Authors: | Escolano, Francisco | Hancock, Edwin R. | Lozano, Miguel Angel | Curado, Manuel |
Research Group/s: | Laboratorio de Investigación en Visión Móvil (MVRLab) |
Center, Department or Service: | Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial |
Keywords: | Graph entropy | Mutual information | Manifold alignment |
Knowledge Area: | Ciencia de la Computación e Inteligencia Artificial |
Issue Date: | 1-Feb-2017 |
Publisher: | Elsevier |
Citation: | Pattern Recognition Letters. 2017, 87: 12-19. doi:10.1016/j.patrec.2016.07.012 |
Abstract: | The estimation of mutual information between graphs has been an elusive problem until the formulation of graph matching in terms of manifold alignment. Then, graphs are mapped to multi-dimensional sets of points through structure preserving embeddings. Point-wise alignment algorithms can be exploited in this context to re-cast graph matching in terms of point matching. Methods based on bypass entropy estimation must be deployed to render the estimation of mutual information computationally tractable. In this paper the novel contribution is to show how manifold alignment can be combined with copula-based entropy estimators to efficiently estimate the mutual information between graphs. We compare the empirical copula with an Archimedean copula (the independent one) in terms of retrieval/recall after graph comparison. Our experiments show that mutual information built in both choices improves significantly state-of-the art divergences. |
Sponsor: | Funding. F. Escolano, M.A. Lozano: Project TIN2012-32839 (Spanish Gov.). M. Curado: BES-2013-064482 (Spanish Gov.). E. R. Hancock: Royal Society Wolfson Research Merit Award. |
URI: | http://hdl.handle.net/10045/68546 |
ISSN: | 0167-8655 (Print) | 1872-7344 (Online) |
DOI: | 10.1016/j.patrec.2016.07.012 |
Language: | eng |
Type: | info:eu-repo/semantics/article |
Rights: | © 2016 Elsevier B.V. |
Peer Review: | si |
Publisher version: | http://dx.doi.org/10.1016/j.patrec.2016.07.012 |
Appears in Collections: | INV - MVRLab - Artículos de Revistas |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
2017_Escolano_etal_PattRecLet_final.pdf | Versión final (acceso restringido) | 1,06 MB | Adobe PDF | Open Request a copy |
2017_Escolano_etal_PattRecLet_revised.pdf | Versión revisada (acceso abierto) | 1,4 MB | Adobe PDF | Open Preview |
Items in RUA are protected by copyright, with all rights reserved, unless otherwise indicated.