Generalized Adjusted Rand Indices for cluster ensembles
Generalized Adjusted Rand Indices for cluster ensembles
复制标题
DOI：
10.1016/j.patcog.2011.11.017
复制
发表时间：
2012-06
期刊：
影响因子：
--
通讯作者：
Shaohong Zhang;Hau-San Wong;Ying Shen
中科院分区：
文献类型：
--
作者：
Shaohong Zhang;Hau-San Wong;Ying Shen
本文将调整后的兰德指数（ARI）推广为两种基于矩阵比较的新测度：（i）相似性矩阵和聚类划分之间的调整后的兰德指数（ARImp），以评估聚类解的集合与聚类集合中它们对应的一致性矩阵的一致性，以及（ii）相似性矩阵之间的调整后的兰德指数（ARImm），以评估两个相似度矩阵之间的一致性。在这两种新的测度中，ARI的一些理想性质得到了保持，并讨论了新的性质。这些属性包括：（i）不相关性的检测;（ii）分布式环境中ARImp/ARImm的计算;以及（iii）一致性矩阵的不确定性程度的表征。从理论分析和实验验证两个角度对这些性质进行了研究。我们还进行了一些实验，以显示的实用性和有效性的两个建议的措施在实际应用中。
In this paper, Adjusted Rand Index (ARI) is generalized to two new measures based on matrix comparison: (i) Adjusted Rand Index between a similarity matrix and a cluster partition (ARImp), to evaluate the consistency of a set of clustering solutions with their corresponding consensus matrix in a cluster ensemble, and (ii) Adjusted Rand Index between similarity matrices (ARImm), to evaluate the consistency between two similarity matrices. Desirable properties of ARI are preserved in the two new measures, and new properties are discussed. These properties include: (i) detection of uncorrelatedness; (ii) computation of ARImp/ARImm in a distributed environment; and (iii) characterization of the degree of uncertainty of a consensus matrix. All of these properties are investigated from both the perspectives of theoretical analysis and experimental validation. We have also performed a number of experiments to show the usefulness and effectiveness of the two proposed measures in practical applications.