Local Pattern Detection in Attributed Graphs

We propose to mine the topology of a large attributed graph by finding regularities among vertex descriptors. Such descriptors are of two types: (1) the vertex attributes that convey the information of the vertices themselves and (2) some topological properties used to describe the connectivity of the vertices. These descriptors are mostly of numerical or ordinal types and their similarity can be captured by quantifying their co-variation. Mining topological patterns relies on frequent pattern mining and graph topology analysis to reveal the links that exist between the relation encoded by the graph and the vertex attributes. In this paper, we study the network of authors who have cooperated at some time with Katharina Morik according to the data available in DBLP database. This is a nice occasion for formalizing different questions that can be considered when an attributed graph describes both a type of interaction and node descriptors.