Presentation | 2003/7/10 Parallel FP-growth Algorithm for Frequent Pattern Mining Eigo IWAHASHI, Hayato YAMANA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Frequent patterns mining is one of the important problem in data mining research. The Apriori is a prominent algorithm followed by many variants. In 2000, the FP-growth, which is reported to be faster than the Apriori, was proposed. However, many parallel algorithms of frequent pattern mining are still based on the Apriori. In this paper, we propose a parallelized version of the FP-growth, which accesses disks in parallel and constructs local FP-trees on each local memory. As a result of the evaluation using 32 node PC cluster, our method is approximately 2 and 130 times faster than sequential FP-growth, when minimum support is 0.25% and 2%, respectively. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Data Mining / Frequent Pattern / Parallel Processing / FP-growth / PC Cluster |
Paper # | DE2003-50 |
Date of Issue |
Conference Information | |
Committee | DE |
---|---|
Conference Date | 2003/7/10(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Data Engineering (DE) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Parallel FP-growth Algorithm for Frequent Pattern Mining |
Sub Title (in English) | |
Keyword(1) | Data Mining |
Keyword(2) | Frequent Pattern |
Keyword(3) | Parallel Processing |
Keyword(4) | FP-growth |
Keyword(5) | PC Cluster |
1st Author's Name | Eigo IWAHASHI |
1st Author's Affiliation | Graduate School of Science and Engineering, Waseda University() |
2nd Author's Name | Hayato YAMANA |
2nd Author's Affiliation | Faculty of Science and Engineering, Waseda University |
Date | 2003/7/10 |
Paper # | DE2003-50 |
Volume (vol) | vol.103 |
Number (no) | 191 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |