@inproceedings{f3f9babd61d241b782fb29cae839df90,
title = "Streaming saturation for large RDF graphs with dynamic schema information",
abstract = "In the Big Data era, RDF data are produced in high volumes. While there exist proposals for reasoning over large RDF graphs using big data platforms, there is a dearth of solutions that do so in environments where RDF data are dynamic, and where new instance and schema triples can arrive at any time. In this work, we present the first solution for reasoning over large streams of RDF data using big data platforms. In doing so, we focus on the saturation operation, which seeks to infer implicit RDF triples given RDF schema constraints. Indeed, unlike existing solutions which saturate RDF data in bulk, our solution carefully identifies the fragment of the existing (and already saturated) RDF dataset that needs to be considered given the fresh RDF statements delivered by the stream. Thereby, it performs the saturation in an incremental manner. Experimental analysis shows that our solution outperforms existing bulk-based saturation solutions.",
keywords = "Big Data, RDF saturation, RDF streams, Spark",
author = "Farvardin, \{Mohammad Amin\} and Dario Colazzo and Khalid Belhajjame and Carlo Sartiani",
note = "Publisher Copyright: {\textcopyright} 2019 Copyright held by the owner/author(s).; 17th ACM SIGPLAN International Symposium on Database Programming Languages, DBPL 2019, co-located with PLDI 2019 ; Conference date: 23-06-2019",
year = "2019",
month = jun,
day = "23",
doi = "10.1145/3315507.3330201",
language = "English",
series = "Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI)",
publisher = "Association for Computing Machinery",
pages = "42--52",
editor = "Alvin Cheung and Kim Nguyen",
booktitle = "DBPL 2019 - Proceedings of the 17th ACM SIGPLAN International Symposium on Database Programming Languages, co-located with PLDI 2019",
}