Hierarchical Classification using Binary Data
Hierarchical Classification using Binary Data
复制标题
DOI：
10.1609/aimag.v40i2.2846
复制
发表时间：
2018-07
期刊：
影响因子：
--
通讯作者：
Denali Molitor;D. Needell
中科院分区：
文献类型：
--
作者：
Denali Molitor;D. Needell
在分类问题中，特别是那些将数据分类到大量类中的问题中，类通常自然地遵循层次结构。也就是说，一些类可能共享相似的结构和功能。这些特征可以通过考虑类标签之间的层次关系来捕获。受最近一种简单的二进制数据分类方法的启发，我们提出了一种适合于对分层数据进行有效分类的变体。在某些设置中，具体地说，当某些类别比其他类别更容易识别时，我们显示了案例计算和准确性的优势。
In classification problems, especially those that categorize data into a large number of classes, the classes often naturally follow a hierarchical structure. That is, some classes are likely to share similar structures and features. Those characteristics can be captured by considering a hierarchical relationship among the class labels. Motivated by a recent simple classification approach on binary data, we propose a variant that is tailored to efficient classification of hierarchical data. In certain settings, specifically, when some classes are significantly easier to identify than others, we show case computational and accuracy advantages.