A novel approach for finding alternative clusterings using feature selection

Authors:
Vinh Thanh Tao;JongHyeok Lee
Affiliations:
Pohang University of Science and Technology, Korea;Pohang University of Science and Technology, Korea
Venue:
DASFAA'12 Proceedings of the 17th international conference on Database Systems for Advanced Applications - Volume Part I
Year:
2012

Citing 7
Cited 0

Feature Selection for Clustering

PADKK '00 Proceedings of the 4th Pacific-Asia Conference on Knowledge Discovery and Data Mining, Current Issues and New Applications
Non-Redundant Data Clustering

ICDM '04 Proceedings of the Fourth IEEE International Conference on Data Mining
Data Mining: Concepts and Techniques

Data Mining: Concepts and Techniques
Comparing Subspace Clusterings

IEEE Transactions on Knowledge and Data Engineering
COALA: A Novel Approach for the Extraction of an Alternate Clustering of High Quality and High Dissimilarity

ICDM '06 Proceedings of the Sixth International Conference on Data Mining
A principled and flexible framework for finding alternative clusterings

Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining
A hierarchical information theoretic technique for the discovery of non linear alternative clusterings

Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining

Quantified Score

Hi-index	0.00

Visualization

Abstract

Alternative clustering algorithms target finding alternative groupings of a dataset, on which traditional clustering algorithms can find only one even though many alternatives could exist. In this research, we propose a method for finding alternative clusterings of a dataset based on feature selection. Using the finding that each clustering has a set of so-called important features, we find the possible important features for the altenative clustering in subsets of data; we transform the data by weighting these features so that the original clustering will not likely to be found in the new data space. We then use the incremental K-means algorithm to directly maximizes the quality of the new clustering found in the new data space. We compare our approach with some previous works on a collection of machine learning datasets and another collection of documents. Our approach was the most stable one as it resulted in different and high quality clusterings in all of the tests. The results showed that by using feature selection, we can improve the dissimilarity between clusterings, and by directly maximizing the clustering quality, we can also achieve better clustering quality than the other approaches.