Inducing Relatedness Graphs for Data Integration

Abstract

In this paper, we present the AbsMatcher system for schema matching which uses a graph based approach. AbsMatcher creates a graph of related attributes within a schema, mines similarity between attributes in different schemas, and then combines all information using the ABSURDIST graph matching algorithm. The focus of this paper is on methods for generating relationships which are semantic in nature, but only require a simple data model. These relationships sources provide a baseline to be used when no others are available. Simulations demonstrate how the use of automatically mined graphs of within-schema relationships, when combined with cross-schema pair-wise similarity, can result in matching accuracy not attainable by either source of information on its own.