G-Hash

Our objective in this chapter is to enable fast similarity search in large graph databases with graph kernel functions. In particular, we propose (i) a novel kernel-based similarity measurement and (ii) an efficient indexing structure for graph data management. In our method, we use a hash table to support efficient storage and fast search of the extracted local features from graph data. Using the hash table, we have developed a graph kernel function to capture the intrinsic similarity of graphs and for fast similarity query processing. We have demonstrated the utility of the proposed methods using large chemical structure graph databases.