@inproceedings{22337bee67244a5ead1cc37bb46ecbe0,
title = "Structural properties as proxy for semantic relevance in RDF graph sampling",
abstract = "The Linked Data cloud has grown to become the largest knowledge base ever constructed. Its size is now turning into a major bottleneck for many applications. In order to facilitate access to this structured information, this paper proposes an automatic sampling method targeted at maximizing answer coverage for applications using SPARQL querying. The approach presented in this paper is novel: no similar RDF sampling approach exist. Additionally, the concept of creating a sample aimed at maximizing SPARQL answer coverage, is unique. We empirically show that the relevance of triples for sampling (a semantic notion) is influenced by the topology of the graph (purely structural), and can be determined without prior knowledge of the queries. Experiments show a significantly higher recall of topology based sampling methods over random and naive baseline approaches (e.g. up to 90% for Open-BioMed at a sample size of 6%).",
keywords = "Graph analysis, Linked data, Ranking, Sampling, Subgraphs",
author = "Laurens Rietveld and Rinke Hoekstra and Stefan Schlobach and Christophe Gu{\'e}ret",
note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2014.; 13th International Semantic Web Conference, ISWC 2014 ; Conference date: 19-10-2014 Through 23-10-2014",
year = "2014",
doi = "10.1007/978-3-319-11915-1_6",
language = "Ingl{\'e}s",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "81--96",
editor = "Peter Mika and Tania Tudorache and Abraham Bernstein and Chris Welty and Craig Knoblock and Denny Vrande{\v c}i{\'c} and Natasha Noy and Paul Groth and Krzysztof Janowicz and Carole Goble",
booktitle = "The Semantic Web - ISWC 2014 - 13th International SemanticWeb Conference, Proceedings",
}