Abstract | ||
---|---|---|
In this paper, we propose a BSP-Based Support Vector Regression Machine Parallel Framework which can implement the most of distributed Support Vector Regression Machine algorithms. The major difference in these algorithms is the network topology among distributed nodes. Therefore, we adopt the Bulk Synchronous Parallel model to solve the strongly connected graph problem in exchanging support vectors among distributed nodes. Besides, we introduce the dynamic algorithms that it can change the strongly connected graph among SVR distributed nodes in every BSP's super-step. The performance of this framework has been analyzed and evaluated with KDD99 data and four DPSVR algorithms with different topology on the high-performance computer. The results proved that the framework can implement the most of distributed SVR algorithms and keep the performance of original algorithm. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/ICIS.2013.6607862 | ICIS |
Keywords | DocType | Volume |
kdd99 data,support vector regression machine (svr),regression analysis,distributed support vector regression machine algorithms,bulk synchronous parallel model,network topology,bsp-based support vector regression machine parallel framework,regression prediction,strongly connected graph problem,parallel algorithms,dpsvr algorithms,graph theory,parallel computing,dynamic algorithms,bulk synchronous parallel,svr distributed nodes,support vector machines | Conference | null |
Issue | ISSN | Citations |
null | 2211-7938 | 0 |
PageRank | References | Authors |
0.34 | 7 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhang Hong | 1 | 18 | 3.74 |
Yong-mei Lei | 2 | 6 | 6.13 |