arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.05849cs.LGstat.ML
收藏

MLPSVM:一种新的并行多标记支持向量机

MLPSVM:A new parallel support vector machine to multi-label learning

CHONGQING NORMAL UNIVERSITY(重庆师范大学)

Yanghong Liu, Jia Lu, Tingting Li

摘要:

多标签学习已经引起了机器学习社区的关注。问题转换方法Binary Relevance将熟悉的单标签转换为多标签算法。二进制相关法由于其结构简单、算法高效而得到广泛应用。但是二进制相关性没有考虑标签之间的联系,这使得处理某些任务变得很麻烦。本文提出了一种多标签学习算法,也可以用于单标签分类。它是在标准支持向量机的基础上,将原有的单决策超平面变为两个并行的决策超平面,称为多标记并行支持向量机(MLPSVM)。文章最后将MLPSVM与其他多标记学习算法进行了比较。实验结果表明,该算法在数据集上具有良好的性能.

英文摘要:

Multi-label learning has attracted the attention of the machine learning community. The problem conversion method Binary Relevance converts a familiar single label into a multi-label algorithm. The binary relevance method is widely used because of its simple structure and efficient algorithm. But binary relevance does not consider the links between labels, making it cumbersome to handle some tasks. This paper proposes a multi-label learning algorithm that can also be used for single-label classification. It is based on standard support vector machines and changes the original single decision hyperplane into two parallel decision hyper-planes, which call multi-label parallel support vector machine (MLPSVM). At the end of the article, MLPSVM is compared with other multi-label learning algorithms. The experimental results show that the algorithm performs well on data sets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑