@inproceedings{a298b5f6868f4753b06e0cecf6374c4f,
title = "Parallel quotient summarization of RDF graphs",
abstract = "Discovering the structure and content of an RDF graph is hard for human users, due to its heterogeneity, complexity, and possibly large size. One class of tools for this task are structural RDF graph summaries, which allow users to grasp the different connections between RDF graph nodes. RDFQuotient graph summaries are a brand of structural summaries we developed. They are usually very compact, making them good for first-sight visual discovery. Existing algorithms for building these summaries are centralized, and require the graph to fit in memory. Going beyond, in this work we present novel algorithms for building RDFQuotient summaries in a parallel, shared-nothing architecture. We instantiate our algorithms to Apache Spark platform; our experiments demonstrate the merit of our approach.",
keywords = "Parallel computations, RDF graphs, Spark, Summarization",
author = "Pawe{\l}t Guzewicz and Ioana Manolescu",
note = "Publisher Copyright: {\textcopyright} 2019 ACM.; 2019 International Workshop on Semantic Big Data, SBD 2019 - In conjunction with the 2019 ACM SIGMOD/PODS Conference ; Conference date: 05-07-2019",
year = "2019",
month = jul,
day = "5",
doi = "10.1145/3323878.3325809",
language = "English",
series = "Proceedings of the ACM SIGMOD International Conference on Management of Data",
publisher = "Association for Computing Machinery",
editor = "Sven Groppe and Le Gruenwald",
booktitle = "Proceedings of the International Workshop on Semantic Big Data, SBD 2019 - In conjunction with the 2019 ACM SIGMOD/PODS Conference",
}