An expressive dissimilarity measure for relational clustering using neighbourhood trees

TL;DR

This paper introduces a comprehensive dissimilarity measure for relational clustering that combines attribute similarity, relational context, and hypergraph proximity, leading to improved clustering performance across diverse datasets.

Contribution

It presents the first similarity measure for relational data that integrates multiple similarity types, addressing biases of existing methods.

Findings

The new measure improves clustering quality on various datasets.

It outperforms existing similarity measures in most cases.

Standard clustering methods benefit from this comprehensive similarity.

Abstract

Clustering is an underspecified task: there are no universal criteria for what makes a good clustering. This is especially true for relational data, where similarity can be based on the features of individuals, the relationships between them, or a mix of both. Existing methods for relational clustering have strong and often implicit biases in this respect. In this paper, we introduce a novel similarity measure for relational data. It is the first measure to incorporate a wide variety of types of similarity, including similarity of attributes, similarity of relational context, and proximity in a hypergraph. We experimentally evaluate how using this similarity affects the quality of clustering on very different types of datasets. The experiments demonstrate that (a) using this similarity in standard clustering methods consistently gives good results, whereas other measures work well only on datasets that match their bias; and (b) on most datasets, the novel similarity outperforms even the best among the existing ones.