On Data Labeling for Clustering Categorical Data

Authors:
Hung-Leng Chen;Kun-Ta Chuang;Ming-Syan Chen
Affiliations:
National Taiwan University, Taipei;Graduate Institute of Communication Engineering, Taipei;National Taiwan University, Taipei
Venue:
IEEE Transactions on Knowledge and Data Engineering
Year:
2008

Citing 0
Cited 5

A data labeling method for clustering categorical data

Expert Systems with Applications: An International Journal
A k-means type clustering algorithm for subspace clustering of mixed numeric and categorical datasets

Pattern Recognition Letters
DHCC: Divisive hierarchical clustering of categorical data

Data Mining and Knowledge Discovery
A novel fuzzy clustering algorithm with between-cluster information for categorical data

Fuzzy Sets and Systems
The k-modes type clustering plus between-cluster information for categorical data

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Sampling has been recognized as an important technique to improve the efficiency of clustering. However, with sampling applied, those points which are not sampled will not have their labels after the normal process. Although there is a straightforward approach in the numerical domain, the problem of how to allocate those unlabeled data points into proper clusters remains as a challenging issue in the categorical domain. In this paper, a mechanism named MAximal Resemblance Data Labeling (abbreviated as MARDL) is proposed to allocate each unlabeled data point into the corresponding appropriate cluster based on the novel categorical clustering representative, namely, N-Nodeset Importance Representative(abbreviated as NNIR), which represents clusters by the importance of the combinations of attribute values. MARDL has two advantages: (1) MARDL exhibits high execution efficiency; (2) MARDL can achieve high intra-cluster similarity and low inter-cluster similarity, which are regarded as the most important properties of clusters, thus benefiting the analysis of cluster behaviors. MARDL is empirically validated on real and synthetic data sets, and is shown to be not only more efficient than prior methods but also attaining results of better quality.