@inproceedings{3636eb52da734c14b1690e4595b3d41c,
title = "Parallel mining of frequent subtree patterns",
abstract = "Mining frequent subtree patterns in a tree database (or, forest) is useful in domains such as bioinformatics and mining semi-structured data. We consider the problem of mining embedded subtrees in a database of rooted, labeled, and ordered trees. We compare two existing serial mining algorithms, PrefixTreeSpan and TreeMiner, and adapt them for parallel execution using PrefixFPM, our general-purpose framework for frequent pattern mining that is designed to effectively utilize the CPU cores in a multicore machine. Our experiments show that TreeMiner is faster than its successor PrefixTreeSpan when a limited number of CPU cores are used, as the total mining workloads is smaller; however, PrefixTreeSpan has a much higher speedup ratio and can beat TreeMiner when given enough CPU cores.",
keywords = "Frequent pattern mining, Parallel, Prefix projection, Tree",
author = "Wenwen Qu and Da Yan and Guimu Guo and Xiaoling Wang and Lei Zou and Yang Zhou",
note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Switzerland AG.; 4th International Workshop on Software Foundations for Data Interoperability, SFDI 2020 and 2nd International Workshop on Large Scale Graph Data Analytics, LSGDA 2020, held in Conjunction with VLDB 2020 ; Conference date: 04-09-2020 Through 04-09-2020",
year = "2020",
doi = "10.1007/978-3-030-61133-0\_2",
language = "英语",
isbn = "9783030611323",
series = "Communications in Computer and Information Science",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "18--32",
editor = "Lu Qin and Wenjie Zhang and Ying Zhang and You Peng and Hiroyuki Kato and Wei Wang and Chuan Xiao",
booktitle = "Software Foundations for Data Interoperability and Large Scale Graph Data Analytics - 4th International Workshop, SFDI 2020, and 2nd International Workshop, LSGDA 2020, held in Conjunction with VLDB 2020, Proceedings",
address = "德国",
}