Clustering evaluation measures are frequently used to evaluate the performance of algorithms. However, most measures are not properly normalized and ignore some information in the inherent structure of clusterings. We model the relation between two clusterings as a bipartite graph and propose a general component-based decomposition formula based on the components of the graph. Most existing measures are examples of this formula. In order to satisfy consistency in the component, we further propose a split-merge framework for comparing clusterings of different data sets. Our framework gives measures that are conditionally normalized, and it can make use of data point information, such as feature vectors and pairwise distances. We use an entropy-based instance of the framework and a coreference resolution data set to demonstrate empirically the utility of our framework over other measures.
|Title of host publication||Proceedings of the 29th International Conference on Machine Learning|
|Subtitle of host publication||ICML 2012 : 26 June-1 July 2012, Edinburgh, Scotland|
|Place of Publication||Germany|
|Publisher||International Machine Learning Society|
|Number of pages||8|
|Publication status||Published - 2012|
|Event||International Conference on Machine Learning (29th : 2012) - Edinburgh, Scotland|
Duration: 26 Jun 2012 → 1 Jul 2012
|Conference||International Conference on Machine Learning (29th : 2012)|
|Period||26/06/12 → 1/07/12|
Xiang, Q., Mao, Q., Chai, K. M. A., Chieu, H. L., Tsang, I. W-H., & Zhao, Z. (2012). A Split-merge framework for comparing clusterings. In Proceedings of the 29th International Conference on Machine Learning: ICML 2012 : 26 June-1 July 2012, Edinburgh, Scotland (Vol. 2, pp. 1055-1062). Germany: International Machine Learning Society.