arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1311.2139cs.LG
收藏

大间隔半监督结构化输出学习

Large Margin Semi-supervised Structured Output Learning

Indian Institute of Science(印度科学学院);Microsoft Research(微软研究院)

P. Balamurugan, Shirish Shevade, Sundararajan Sellamanickam

摘要:

在结构化输出学习中,为现实世界的应用程序获取标记的数据通常是昂贵的,而未标记的示例则大量存在。半监督结构化分类已被开发用于处理大量未标记的结构化数据。在这项工作中,我们考虑半监督结构支持向量机域约束。优化问题,这在一般情况下是不凸的,包含与标记和未标记的例子以及域约束相关的损失项。我们提出了一个简单的优化方法,交替解决一个监督学习问题和约束匹配问题。针对结构化预测难以解决的约束匹配问题,提出了一种高效的爬山算法,在确定性退火框架下进行交替优化,有效地进行约束匹配,避免了局部极小值的产生.该算法实现简单,在基准数据集上取得了相当的泛化性能。

英文摘要:

In structured output learning, obtaining labelled data for real-world applications is usually costly, while unlabelled examples are available in abundance. Semi-supervised structured classification has been developed to handle large amounts of unlabelled structured data. In this work, we consider semi-supervised structural SVMs with domain constraints. The optimization problem, which in general is not convex, contains the loss terms associated with the labelled and unlabelled examples along with the domain constraints. We propose a simple optimization approach, which alternates between solving a supervised learning problem and a constraint matching problem. Solving the constraint matching problem is difficult for structured prediction, and we propose an efficient and effective hill-climbing method to solve it. The alternating optimization is carried out within a deterministic annealing framework, which helps in effective constraint matching, and avoiding local minima which are not very useful. The algorithm is simple to implement and achieves comparable generalization performance on benchmark datasets.

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。

↑