期刊
DATA MINING AND KNOWLEDGE DISCOVERY
卷 36, 期 3, 页码 958-986出版社
SPRINGER
DOI: 10.1007/s10618-022-00820-9
关键词
Subspace clustering; Constrained clustering; Active learning
资金
- EPSRC [EP/L015692/1]
- Office for National Statistics (ONS)
In this paper, a novel spectral-based subspace clustering algorithm is proposed and extended to a constrained clustering and active learning framework. Extensive experiments show that the proposed approach is effective and competitive with state-of-the-art methods.
Spectral-based subspace clustering methods have proved successful in many challenging applications such as gene sequencing, image recognition, and motion segmentation. In this work, we first propose a novel spectral-based subspace clustering algorithm that seeks to represent each point as a sparse convex combination of a few nearby points. We then extend the algorithm to a constrained clustering and active learning framework. Our motivation for developing such a framework stems from the fact that typically either a small amount of labelled data are available in advance; or it is possible to label some points at a cost. The latter scenario is typically encountered in the process of validating a cluster assignment. Extensive experiments on simulated and real datasets show that the proposed approach is effective and competitive with state-of-the-art methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据