SPINEX-Clustering: Similarity-based Predictions with Explainable Neighbors Exploration for Clustering Problems

TL;DR

This paper introduces SPINEX-Clustering, a novel similarity-based clustering algorithm that leverages higher-order interactions and offers explainability, demonstrating competitive performance and moderate complexity across diverse datasets.

Contribution

The paper proposes SPINEX-Clustering, a new algorithm that combines similarity measures and explainability, with extensive benchmarking and complexity analysis.

Findings

SPINEX outperforms many existing clustering algorithms in top-5 rankings.

The algorithm demonstrates moderate computational complexity.

SPINEX offers explainability features for clustering results.

Abstract

This paper presents a novel clustering algorithm from the SPINEX (Similarity-based Predictions with Explainable Neighbors Exploration) algorithmic family. The newly proposed clustering variant leverages the concept of similarity and higher-order interactions across multiple subspaces to group data into clusters. To showcase the merit of SPINEX, a thorough set of benchmarking experiments was carried out against 13 algorithms, namely, Affinity Propagation, Agglomerative, Birch, DBSCAN, Gaussian Mixture, HDBSCAN, K-Means, KMedoids, Mean Shift, MiniBatch K-Means, OPTICS, Spectral Clustering, and Ward Hierarchical. Then, the performance of all algorithms was examined across 51 synthetic and real datasets from various domains, dimensions, and complexities. Furthermore, we present a companion complexity analysis to compare the complexity of SPINEX to that of the aforementioned algorithms. Our results demonstrate that SPINEX can outperform commonly adopted clustering algorithms by ranking within the top-5 best performing algorithms and has moderate complexity. Finally, a demonstration of the explainability capabilities of SPINEX, along with future research needs, is presented.