Other formats:
BibTeX
LaTeX
RIS
@inproceedings{1371735,
author = {Míč, Vladimír and Novák, David and Zezula, Pavel},
address = {USA},
booktitle = {2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW)},
doi = {http://dx.doi.org/10.1109/ICDMW.2016.0098},
editor = {Carlotta Domeniconi, Francesco Gullo, Francesco Bonchi, Josep Domingo-Ferrer, Ricardo Baeza-Yates, Zhi-Hua Zhou, Xindong Wu},
keywords = {Algorithm;Similarity search;Similarity filtering;Bit strings;Sketches;Hamming distance},
howpublished = {tištěná verze "print"},
language = {eng},
location = {USA},
isbn = {978-1-5090-5472-5},
pages = {655-662},
publisher = {IEEE},
title = {Designing Sketches for Similarity Filtering},
url = {http://ieeexplore.ieee.org/document/7836729/},
year = {2016}
}
TY - JOUR
ID - 1371735
AU - Míč, Vladimír - Novák, David - Zezula, Pavel
PY - 2016
TI - Designing Sketches for Similarity Filtering
PB - IEEE
CY - USA
SN - 9781509054725
KW - Algorithm;Similarity search;Similarity filtering;Bit strings;Sketches;Hamming distance
UR - http://ieeexplore.ieee.org/document/7836729/
N2 - Abstract: The amounts of currently produced data emphasize the importance of techniques for efficient data processing. Searching big data collections according to similarity of data well corresponds to human perception. This paper is focused on similarity search using the concept of sketches – a compact bit string representations of data objects compared by Hamming distance, which can be used for filtering big datasets. The object-to-sketch transformation is a form of the dimensionality reduction and thus there are two basic contradictory requirements: (1) The length of the sketches should be small for efficient manipulation, but (2) longer sketches retain more information about the data objects. First, we study various sketching methods for data modeled by metric space and we analyse their quality. Specifically, we study importance of several sketch properties for similarity search and we propose a high quality sketching technique. Further, we focus on the length of sketches by studying mutual influence of sketch properties such as correlation of their bits and the intrinsic dimensionality of a set of sketches. The outcome is an equation that allows us to estimate a suitable length of sketches for an arbitrary given dataset. Finally, we empirically verify proposed approach on two real-life datasets.
ER -
MÍČ, Vladimír, David NOVÁK and Pavel ZEZULA. Designing Sketches for Similarity Filtering. In Carlotta Domeniconi, Francesco Gullo, Francesco Bonchi, Josep Domingo-Ferrer, Ricardo Baeza-Yates, Zhi-Hua Zhou, Xindong Wu. \textit{2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW)}. USA: IEEE, 2016, p.~655-662. ISBN~978-1-5090-5472-5. Available from: https://dx.doi.org/10.1109/ICDMW.2016.0098.
|
