Abstract
Most pattern recognition approaches look for patterns in data represented as independent entities described by attributes. However, the relationships between entities are as important, if not more important, to the recognition of accurate and meaningful patterns. In this chapter we describe an approach to discovering patterns in relational data represented as a graph. Our approach is based on the minimum description length (MDL) principle [28], which measures how well various patterns compress the original database. This approach is implemented in the SUBDUE system. We begin with a discussion of related work. We then describe graph-based discovery, the main discovery algorithm, and the polynomially-constrained inexact graph matching algorithm at the heart of the discovery process. Next, we describe how this technique can also be used for clustering and concept learning. We illustrate the utility of the approach by applying the clustering and concept learning techniques to DNA and WWW data.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
