BSP-based support vector regression machine parallel framework

Author

Hong Zhang ; Yongmei Lei

Author_Institution

Sch. of Comput. Eng. & Sci., Shanghai Univ., Shanghai, China

fYear

2013

fDate

16-20 June 2013

Firstpage

329

Lastpage

334

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.

Keywords

graph theory; parallel algorithms; regression analysis; support vector machines; BSP-based support vector regression machine parallel framework; DPSVR algorithms; KDD99 data; SVR distributed nodes; bulk synchronous parallel model; distributed support vector regression machine algorithms; dynamic algorithms; network topology; strongly connected graph problem; Algorithm design and analysis; Computational modeling; Heuristic algorithms; Network topology; Support vector machines; Topology; Training; bulk synchronous parallel; parallel computing; regression prediction; support vector regression machine (SVR);

fLanguage

English

Publisher

ieee

Conference_Titel

Computer and Information Science (ICIS), 2013 IEEE/ACIS 12th International Conference on

Conference_Location

Niigata

Type

conf

DOI

10.1109/ICIS.2013.6607862

Filename

6607862