Multitask multiclass support vector machines: Model and experiments
Multitask multiclass support vector machines: Model and experiments
复制标题
DOI：
10.1016/j.patcog.2012.08.010
复制
发表时间：
2013-03-01
影响因子：
8
通讯作者：
Sun, Shiliang
中科院分区：
文献类型：
--
作者：
Ji, You;Sun, Shiliang
多任务学习或同时学习多个相关任务比独立学习这些任务表现出更好的性能。大多数多任务多类问题的方法将其分解为多个多任务二进制问题，因此无法有效地捕获类之间的内在相关性。虽然非常优雅，但传统的多任务支持向量机受到不同学习任务必须共享同一组类的事实的限制。在本文中，我们提出了一种基于正则化泛函最小化的多任务多类支持向量机方法。我们将多任务多类问题转化为一个具有二次目标函数的约束优化问题。因此，我们的方法可以直接有效地学习多任务多类问题。这种方法可以在两种不同的情况下学习：标签兼容和标签不兼容的多任务学习。我们可以很容易地将线性多任务学习方法推广到使用核的非线性情况。大量的实验，包括与其他多任务学习方法的比较，表明我们的多任务多类问题的方法是非常令人鼓舞的。(C)2012爱思唯尔有限公司版权所有。
Multitask learning or learning multiple related tasks simultaneously has shown a better performance than learning these tasks independently. Most approaches to multitask multiclass problems decompose them into multiple multitask binary problems, and thus cannot effectively capture inherent correlations between classes. Although very elegant, traditional multitask support vector machines are restricted by the fact that different learning tasks have to share the same set of classes. In this paper, we present an approach to multitask multiclass support vector machines based on the minimization of regularization functionals. We cast multitask multiclass problems into a constrained optimization problem with a quadratic objective function. Therefore, our approach can learn multitask multiclass problems directly and effectively. This approach can learn in two different scenarios: label-compatible and label-incompatible multitask learning. We can easily generalize the linear multitask learning method to the non-linear case using kernels. A number of experiments, including comparisons with other multitask learning methods, indicate that our approach for multitask multiclass problems is very encouraging. (C) 2012 Elsevier Ltd. All rights reserved.