@inproceedings{5b36703308814e7c97cd93826c4b10e0,
title = "Similarity Grouping in Big Data Systems",
abstract = "Distributed computing technologies have opened the door for a wide range of organizations to analyze massive amounts of data. Grouping (fast but based on exact semantics) and clustering (relatively slow but based on similarity-aware semantics) are among the most useful data analysis operations. Previous work introduced the Similarity Grouping (SG) operator, which aims to integrate the best features of grouping and clustering, i.e., fast execution times and similarity-aware grouping semantics. The SG operators, however, were proposed for single node relational database systems. This paper introduces the Distributed Similarity Grouping (DSG) operator, a highly parallel operator for identifying similarity groups in big datasets. DSG enables the identification of groups where all the elements are within a given threshold from each other. This paper presents DSG{\textquoteright}s design details, implementation guidelines on Spark and Hadoop (two important Big Data systems), and extensive performance and scalability evaluation.",
keywords = "Big data systems, Clustering, Hadoop, MapReduce, Performance evaluation, Similarity grouping, Spark",
author = "Silva, {Yasin N.} and Manuel Sandoval and Diana Prado and Xavier Wallace and Chuitian Rong",
note = "Publisher Copyright: {\textcopyright} 2019, Springer Nature Switzerland AG.; 12th International Conference on Similarity Search and Applications, SISAP 2019 ; Conference date: 02-10-2019 Through 04-10-2019",
year = "2019",
doi = "10.1007/978-3-030-32047-8_19",
language = "English (US)",
isbn = "9783030320461",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer",
pages = "212--220",
editor = "Giuseppe Amato and Claudio Gennaro and Vincent Oria and Milo{\v s} Radovanovic",
booktitle = "Similarity Search and Applications - 12th International Conference, SISAP 2019, Proceedings",
}