A data quality framework for graph-based virtual data integration systems

Abstract

Data Quality (DQ) plays a critical role in data integration. Up to now, DQ has mostly been addressed from a single database perspective. Popular DQ frameworks rely on Integrity Constraints (IC) to enforce valid application semantics, which lead to the Denial Constraint (DC) formalism which models a broad range of ICs in real-world applications. Yet, current approaches are rather monolithic, considering a single database and do not suit data integration scenarios. In this paper, we address DQ for data integration systems. Specifically, we extend virtual data integration systems to elicit DCs from disparate data sources to be integrated, using DC-related state-of-the-art, and propagate them to the integrated schema (global DCs). Then, we propose a method to manage global DCs and identify (i) minimal DCs and (ii) potential clashes between them.