A hierarchical method for multi-class support vector machines
A hierarchical method for multi-class support vector machines
复制标题
DOI：
10.1145/1015330.1015427
复制
发表时间：
2004-07
期刊：
影响因子：
--
通讯作者：
Volkan Vural;Jennifer G. Dy
中科院分区：
文献类型：
--
作者：
Volkan Vural;Jennifer G. Dy
我们引入了一个框架，我们称之为除以2（DB2），支持向量机（SVM）扩展到多类问题。DB2提供了标准一对一和一对其余算法的替代方案。对于一个N类问题，DB2生成一个N-1节点的二叉决策树，其中节点表示由N-1个SVM二叉分类器形成的决策边界。这个树结构允许我们对DB2进行概括和时间复杂度分析。我们的分析和相关实验表明，DB2在测试时间方面比one-against-one和one-against-rest算法快，在训练时间方面明显快于one-against-rest算法，并且DB2的交叉验证准确率与这两种方法相当。
We introduce a framework, which we call Divide-by-2 (DB2), for extending support vector machines (SVM) to multi-class problems. DB2 offers an alternative to the standard one-against-one and one-against-rest algorithms. For an N class problem, DB2 produces an N − 1 node binary decision tree where nodes represent decision boundaries formed by N − 1 SVM binary classifiers. This tree structure allows us to present a generalization and a time complexity analysis of DB2. Our analysis and related experiments show that, DB2 is faster than one-against-one and one-against-rest algorithms in terms of testing time, significantly faster than one-against-rest in terms of training time, and that the cross-validation accuracy of DB2 is comparable to these two methods.