Finding frequent structures in semistructured data

Numerous graph-based frequent pattern mining algorithms have been developed in the past. Identifying frequent structures involves locating sub graphs that occur frequently over the entire set of graphs. In this paper an experimental comparison of two graph-based algorithms for identifying frequent structures in semi-structured data has been presented and discussed in this paper. The SEuS algorithm for recognizing frequent structures has been explored and the results are compared with the SUBDUE algorithm. An analysis of the experimental results indicates that pin pointing frequent structures in a huge graph using SEuS algorithm is faster compared to the SUBDUE algorithm. The computational complexity oflocating frequent structures in SEuS algorithm has been overcome using a summary data structure which prunes the search space. � 2009 ISSN.