Moderated class-membership interchange in iterative multi-relational graph classifier

Abstract

Organizing information resources into classes helps significantly in searching in massive volumes of on line documents available through the Web or other information sources such as electronic mail, digital libraries, corporate databases. Existing classification methods are often based only on own content of document, i.e. its attributes. Considering relations in the web document space brings better results. We adopt multi-relational classification that interconnects attribute-based classifiers with iterative optimization based on relational heterogeneous graph structures, while different types of instances and various relation types can be classified together. We establish moderated class-membership spreading mechanism in multi-relational graphs and compare the impact of various levels of regulation in collective inference classifier. The experiments based on large-scale graphs originated in MAPEKUS research project data set (web portals of scientific libraries) demonstrate that moderated class-membership spreading significantly increases accuracy of the relational classifier (up to 10%) and protects instances with heterophilic neighborhood to be misclassified. © Springer-Verlag Berlin Heidelberg 2010.