Graph search beyond text: Relational searches in semantic hyperlinked data

Abstract

We present novel indexing and searching schemes for semantic graphs based on the notion of the i.degrees of a node. The i.degrees allow searches performed on the graph to use “type” and connection information, rather than textual labels, to identify nodes. We aim to identify a network graph (fragment) within a large semantic graph (database). A fragment may represent incomplete information that a researcher has collected on a sub-network of interest. While textual labels might be available, they are highly unreliable, and cannot be used for identification of hidden networks. Since this problem comes from the classically NP-hard problem of identifying isomorphic subgraphs, our algorithms are heuristic.