Graph-Based Hierarchical Conceptual Clustering in Structural Databases

Hierarchical conceptual clustering has been proven to be a useful, although greatly under-explored data mining technique. A graph-based representation of structural information combined with a substructure discovery technique has been shown to be successful in knowledge discovery. The SUBDUE substructure discovery system provides the advantages of both approaches. This work presents a new algorithm that uses SUBDUE to build conceptual clustering hierarchies. An example is used to illustrate the validity of the approach.

Authors

• Istvan Jonyer Lawrence B. Holder
• and Diane J. Cook University of Texas at Arlington

Keywords

No keywords are indexed for this paper.