@inproceedings{aeccdb5a99a347a8a80f7af3b2210e4b,
title = "ATreeGrep: Approximate searching in unordered trees",
abstract = "An unordered labeled tree is a tree in which each node has a string label and the parent-child relationship is significant, but the order among siblings is unimportant. This paper presents an approach to the nearest neighbor search problem for these trees. Given a database D of unordered labeled trees and a query tree Q, the goal is to find those trees in D that {"}approximately{"} contain Q. Our approach is based on storing the paths of the trees in a suffix array and then counting the number of mismatching paths between the query tree and a data tree. To speed up a search, we use a hash-based technique to filter out unqualified data trees at an early stage of the search. Experimental results obtained by running our techniques on phylogenetic trees and synthetic data demonstrate the good performance of the proposed approach. We also discuss the use of our work in XML and scientific database management.",
keywords = "Algorithm design and analysis, Change detection algorithms, Computer science, Decision trees, Filters, Nearest neighbor searches, Object oriented databases, Object oriented modeling, Phylogeny, XML",
author = "D. Shasha and Wang, {J. T.L.} and Huiyuan Shan and Kaizhong Zhang",
note = "Publisher Copyright: {\textcopyright} 2002 IEEE.; 14th International Conference on Scientific and Statistical Database Management, SSDBM 2002 ; Conference date: 24-07-2002 Through 26-07-2002",
year = "2002",
doi = "10.1109/SSDM.2002.1029709",
language = "English (US)",
series = "Proceedings of the International Conference on Scientific and Statistical Database Management, SSDBM",
publisher = "IEEE Computer Society",
pages = "89--98",
editor = "Jessie Kennedy",
booktitle = "Proceedings - 14th International Conference on Scientific and Statistical Database Management, SSDBM 2002",
}