%0 Conference Proceedings
%T Graph Embedding through Probabilistic Graphical Model applied to Symbolic Graphs
%A Hana Jarraya
%A Oriol Ramos Terrades
%A Josep Llados
%B 8th Iberian Conference on Pattern Recognition and Image Analysis
%D 2017
%F Hana Jarraya2017
%O DAG; 600.097; 600.121
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2953), last updated on Fri, 21 Jan 2022 14:27:10 +0100
%X We propose a new Graph Embedding (GEM) method that takes advantages of structural pattern representation. It models an Attributed Graph (AG) as a Probabilistic Graphical Model (PGM). Then, it learns the parameters of this PGM presented by a vector. This vector is a signature of AG in a lower dimensional vectorial space. We apply Structured Support Vector Machines (SSVM) to process classification task. As first tentative, results on the GREC dataset are encouraging enough to go further on this direction.
%K Attributed Graph
%K Probabilistic Graphical Model
%K Graph Embedding
%K Structured Support Vector Machines
%U https://doi.org/10.1007/978-3-319-58838-4_43
%U http://refbase.cvc.uab.es/files/JRL2017a.pdf