2008 | OriginalPaper | Buchkapitel
Generalized Graph Matching for Data Mining and Information Retrieval
verfasst von : Alexandra Brügger, Horst Bunke, Peter Dickinson, Kaspar Riesen
Erschienen in: Advances in Data Mining. Medical Applications, E-Commerce, Marketing, and Theoretical Aspects
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Graph based data representation offers a convenient possibility to represent entities, their attributes, and their relationships to other entities. Consequently, the use of graph based representation for data mining has become a promising approach to extracting novel and useful knowledge from relational data. In order to check whether a certain graph occurs, as a substructure, within a larger database graph, the widely studied concept of subgraph isomorphism can be used. However, this conventional approach is rather limited. In the present paper the concept of subgraph isomorphism is substantially extended such that it can cope with don’t care symbols, variables, and constraints. Our novel approach leads to a powerful graph matching methodology which can be used for advanced graph based data mining.