Fast Frequent Itemset Mining from Uncertain Databases using GPGPU
Graduate School of Systems and Information Engineering, University of Tsukuba
The Fifth International VLDB Workshop on Management of Uncertain Data, 2011
@inproceedings{kozawa2011fast,
title={Fast Frequent Itemset Mining from Uncertain Databases using GPGPU},
author={Kozawa, Y. and Amagasa, T. and Kitagawa, H.},
booktitle={The Fifth International VLDB Workshop on Management of Uncertain Data},
pages={17},
year={2011}
}
Frequent itemset mining from uncertain databases is different from conventional one in the sense that it needs to take into account uncertainty. To this end, some methods have already been proposed, but their performances are not satisfactory. Meanwhile, GPGPU (General Purpose computing on GPU) have recently been an interesting research subject in the field of high performance computing. GPGPU is to use GPU (Graphics Processing Unit), which is originally designed for processing graphics, for general purpose computation. In this paper, we propose a method for fast frequent itemset mining from uncertain databases using GPGPU. In addition, experiments show that our proposed method is up to 30 times faster than an existing method.
September 27, 2011 by hgpu
