Clustering based on Random Graph Model embedding Vertex Features

TL;DR

This paper introduces a novel graph clustering algorithm that leverages both vertex features and connectivity patterns within a statistical model, improving clustering accuracy in datasets with rich interaction data.

Contribution

The paper presents a new clustering method combining vertex features and graph topology using a latent structure model, outperforming existing approaches.

Findings

Algorithm effectively exploits both features and connectivity.

Simulation results show improved clustering accuracy.

Real dataset analysis confirms practical utility.

Abstract

Large datasets with interactions between objects are common to numerous scientific fields (i.e. social science, internet, biology...). The interactions naturally define a graph and a common way to explore or summarize such dataset is graph clustering. Most techniques for clustering graph vertices just use the topology of connections ignoring informations in the vertices features. In this paper, we provide a clustering algorithm exploiting both types of data based on a statistical model with latent structure characterizing each vertex both by a vector of features as well as by its connectivity. We perform simulations to compare our algorithm with existing approaches, and also evaluate our method with real datasets based on hyper-textual documents. We find that our algorithm successfully exploits whatever information is found both in the connectivity pattern and in the features.