一种基于支持向量机的并行训练策略

上海大学学报(自然科学版)

一种基于支持向量机的并行训练策略

雷咏梅，王雄，郭恒明，金亨科

上海大学计算机工程与科学学院，上海 200072

收稿日期:2007-05-08 修回日期:1900-01-01 出版日期:2007-10-20 发布日期:2007-10-20
通讯作者: 雷咏梅

Parallel Training Strategy Based on Support Vector Machine

LEI Yong-mei,WANG Xiong,GUO Heng-ming,JIN Heng-ke

School of Computer Engineering and Science, Shanghai University, Shanghai 200072, China

Received:2007-05-08 Revised:1900-01-01 Online:2007-10-20 Published:2007-10-20
Contact: LEI Yong-mei

摘要/Abstract

摘要： 针对基于支持向量机的分类器训练时间过长问题，提出一种并行训练策略.该策略在并行程序设计上采用主从模式，将训练任务划分成若干个子任务，分配到多个从节点上计算，最后由主节点将各从节点上的训练结果收集，生成分类器模型.采用这种算法，使用了多组稀疏型和连续型的数据集，经过在自强3000高性能计算机上测试，实验结果表明该算法不仅能够保证多分类的高准确率，而且缩短了训练时间.

关键词: 并行计算, 并行训练, 决策函数(df), 支持向量机(SVM)

Abstract: We propose a parallel training strategy, which is an improved parallel algorithm of support vector machine (SVM), to shorten the training time based on SVM's classification. The strategy uses the master-salve mode and divides the whole training task into several subtasks, each sub-task computed by a node. The master node collects the training results from slave nodes to produce the classifiable model. Performance of this algorithm is analyzed and evaluated with sparse and dense dataset on a high-performance computer ZQ3000 cluster. The results indicate that the proposed method can ensure high precision in the original multi-classification and reduce training time.

Key words: decision-function, parallel training, support vector machine (SVM), parallel computing

雷咏梅;王雄;郭恒明;金亨科. 一种基于支持向量机的并行训练策略[J]. 上海大学学报(自然科学版).

LEI Yong-mei;WANG Xiong;GUO Heng-ming;JIN Heng-ke. Parallel Training Strategy Based on Support Vector Machine[J]. Journal of Shanghai University（Natural Science Edition）.