A recursive embedding approach to median graph computation

The median graph has been shown to be a good choice to infer a representative of a set of graphs. It has been successfully applied to graph-based classification and clustering. Nevertheless, its computation is extremely complex. Several approaches have been presented up to now based on different str...

ver descrição completa

Detalhes bibliográficos
Autores: Ferrer Sumsi, Miquel, Valveny, Ernest, Bunke, Horst
Tipo de documento: capítulo de livro
Data de publicação:2009
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositório:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglês
OAI Identifier:oai:upcommons.upc.edu:2117/7811
Acesso em linha:https://hdl.handle.net/2117/7811
https://dx.doi.org/10.1007/978-3-642-02124-4_12
Access Level:Acceso aberto
Palavra-chave:Pattern recognition systems
Reconeixement de formes (Informàtica)
Classificació INSPEC::Pattern recognition
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Reconeixement de formes
Descrição
Resumo:The median graph has been shown to be a good choice to infer a representative of a set of graphs. It has been successfully applied to graph-based classification and clustering. Nevertheless, its computation is extremely complex. Several approaches have been presented up to now based on different strategies. In this paper we present a new approximate recursive algorithm for median graph computation based on graph embedding into vector spaces. Preliminary experiments on three databases show that this new approach is able to obtain better medians than the previous existing approaches.