 |
 |
 |
Conference papers
A Scalable MapReduce Similarity Join Computation Using LSH
Abstract : Similarity joins are recognized to be among the most useful data process-
ing and analysis operations. A similarity join is used to retrieve all data pairs whose
distances are smaller than a predefined threshold λ .
In this paper, we introduce the MRS-join algorithm to perform similarity joins on
large trajectories datasets. The MapReduce model and a randomized LSH (Local
Sensitive Hashing) keys redistribution approach are used to balance load among pro-
cessing nodes while reducing communications and computations to almost all rele-
vant data by using distributed histograms.
A cost analysis of the MRS-join algorithm shows that our approach is insensitive to
data skew and guarantees perfect balancing properties, in large scale systems, during
all stages of similarity join computations. These performances have been confirmed
by a series of experiments using the Fréchet distance on large datasets of trajectories
from real world and synthetic data benchmarks.
https://hal-univ-orleans.archives-ouvertes.fr/hal-03526678
Contributor : Sébastien Limet Connect in order to contact the contributor
Submitted on : Friday, January 14, 2022 - 4:23:24 PM
Last modification on : Saturday, January 15, 2022 - 3:24:47 AM
Contributor : Sébastien Limet Connect in order to contact the contributor
Submitted on : Friday, January 14, 2022 - 4:23:24 PM
Last modification on : Saturday, January 15, 2022 - 3:24:47 AM