Presentation | 2007-07-03 Parallel Frequent Pattern Mining Method from Super-High-Dimensional Data by Vertical Partitioning Kouichirou MORI, Ryohei ORIHARA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In general, traditional parallel frequent pattern mining methods were applied to data that contains a large number of records. The data was horizontally partitioned and each partitioned data was allocated to processing elements. However recently, frequent pattern mining from super-high-dimensional data that contains a huge number of attributes is becoming important. The traditional parallel frequent pattern mining methods cannot handle these data. In this paper, we show that the combination of vertical partitioning and record space search is efficient for parallel frequent pattern mining of high-dimensional data. We evaluate our method with real microarray dataset on 16 PCs to discover that it is approximately 13 times faster than sequential one. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Data Mining / Association Rule / Frequent Pattern / High Dimensional Data / Vertical Partitioning / Parallel Processing |
Paper # | DE2007-91 |
Date of Issue |
Conference Information | |
Committee | DE |
---|---|
Conference Date | 2007/6/25(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 Frequent Pattern Mining Method from Super-High-Dimensional Data by Vertical Partitioning |
Sub Title (in English) | |
Keyword(1) | Data Mining |
Keyword(2) | Association Rule |
Keyword(3) | Frequent Pattern |
Keyword(4) | High Dimensional Data |
Keyword(5) | Vertical Partitioning |
Keyword(6) | Parallel Processing |
1st Author's Name | Kouichirou MORI |
1st Author's Affiliation | Research & Development Center, Toshiba Corporation() |
2nd Author's Name | Ryohei ORIHARA |
2nd Author's Affiliation | Research & Development Center, Toshiba Corporation |
Date | 2007-07-03 |
Paper # | DE2007-91 |
Volume (vol) | vol.107 |
Number (no) | 131 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |