RDB2RDF mapping has been a hot topic in the Semantic Web research community. In order to standardize the mapping mechanism and then facilitate sharing and reuse of the mapping definitions, the W3C RDB2RDF Working Group published a general purpose RDB2RDF mapping language standard, R2RML, in September 2012. Several mapping tools or ongoing projects have been gradually supporting the R2RML standard. But they rarely write up and report the design and implementation techniques for the mapping algorithms. This paper presents the algorithm design of a prototype R2RML processor for materializing RDF view of relational data. Experimental tests on the effectiveness and the run-time efficiency of the algorithm were conducted with the W3C-defined R2RML mapping test cases. The experimental results show that the proposed RDB2RDF mapping approach is implementable with Java language, and the run-time of the algorithm exhibits a linear growth rate as the generated RDF triples size increases.
Information bottleneck is an information-theoretic principle of representation learning that aims to learn a maximally compressed representation that preserves as much information about labels as possible. Under this principle, two different methods have been proposed, i.e., information bottleneck (IB) and deterministic information bottleneck (DIB), and have gained significant progress in explaining the representation mechanisms of deep learning algorithms. However, these theoretical and empirical successes are only valid with the assumption that training and test data are drawn from the same distribution, which is clearly not satisfied in many real-world applications. In this paper, we study their generalization abilities within a transfer learning scenario, where the target error could be decomposed into three components, i.e., source empirical error, source generalization gap (SG), and representation discrepancy (RD). Comparing IB and DIB on these terms, we prove that DIB’s SG bound is tighter than IB’s while DIB’s RD is larger than IB’s. Therefore, it is difficult to tell which one is better. To balance the trade-off between SG and the RD, we propose an elastic information bottleneck (EIB) to interpolate between the IB and DIB regularizers, which guarantees a Pareto frontier within the IB framework. Additionally, simulations and real data experiments show that EIB has the ability to achieve better domain adaptation results than IB and DIB, which validates the correctness of our theories.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.