An Agent-Based Algorithm exploiting Multiple Local Dissimilarities for Clusters Mining and Knowledge Discovery

TL;DR

This paper introduces a multi-agent clustering algorithm that autonomously discovers relevant data regularities and optimal dissimilarity measure configurations, producing interpretable and well-separated clusters.

Contribution

It presents a novel multi-agent approach that explores multiple dissimilarity configurations simultaneously for improved cluster discovery and interpretability.

Findings

Successfully discovers consistent and interpretable clusters.

Performs comparably to state-of-the-art clustering algorithms.

Automatically identifies optimal dissimilarity parameters.

Abstract

We propose a multi-agent algorithm able to automatically discover relevant regularities in a given dataset, determining at the same time the set of configurations of the adopted parametric dissimilarity measure yielding compact and separated clusters. Each agent operates independently by performing a Markovian random walk on a suitable weighted graph representation of the input dataset. Such a weighted graph representation is induced by the specific parameter configuration of the dissimilarity measure adopted by the agent, which searches and takes decisions autonomously for one cluster at a time. Results show that the algorithm is able to discover parameter configurations that yield a consistent and interpretable collection of clusters. Moreover, we demonstrate that our algorithm shows comparable performances with other similar state-of-the-art algorithms when facing specific clustering problems.