Break the Tie: Learning Cluster-Customized Category Relationships for Categorical Data Clustering

TL;DR

This paper introduces a novel clustering method that learns customized relationships between categorical attribute categories, improving clustering accuracy especially in mixed datasets by relaxing fixed relationship assumptions.

Contribution

It proposes a new approach to learn category relationships that are adaptable and Euclidean-compatible, enhancing clustering performance over fixed-relationship methods.

Findings

Significantly improved clustering accuracy on benchmark datasets.

Learned category relationships are Euclidean distance metric-compatible.

Outperforms existing methods with an average ranking of 1.25.

Abstract

Categorical attributes with qualitative values are ubiquitous in cluster analysis of real datasets. Unlike the Euclidean distance of numerical attributes, the categorical attributes lack well-defined relationships of their possible values (also called categories interchangeably), which hampers the exploration of compact categorical data clusters. Although most attempts are made for developing appropriate distance metrics, they typically assume a fixed topological relationship between categories when learning distance metrics, which limits their adaptability to varying cluster structures and often leads to suboptimal clustering performance. This paper, therefore, breaks the intrinsic relationship tie of attribute categories and learns customized distance metrics suitable for flexibly and accurately revealing various cluster distributions. As a result, the fitting ability of the clustering algorithm is significantly enhanced, benefiting from the learnable category relationships. Moreover, the learned category relationships are proved to be Euclidean distance metric-compatible, enabling a seamless extension to mixed datasets that include both numerical and categorical attributes. Comparative experiments on 12 real benchmark datasets with significance tests show the superior clustering accuracy of the proposed method with an average ranking of 1.25, which is significantly higher than the 5.21 ranking of the current best-performing method.