Approximate spectral clustering with eigenvector selection and self-tuned $k$

TL;DR

This paper introduces an approximate spectral clustering algorithm that automatically estimates the number of clusters and selects eigenvectors using relevance metrics, improving efficiency and usability for large datasets.

Contribution

It proposes a novel ASC method with automatic $k$ estimation using relevance metrics and GNG for eigenvector selection, enhancing practicality and performance.

Findings

Efficient clustering comparable to manual $k$ methods

Automatic $k$ estimation improves usability

GNG preserves data topology effectively

Abstract

The recently emerged spectral clustering surpasses conventional clustering methods by detecting clusters of any shape without the convexity assumption. Unfortunately, with a computational complexity of $O(n^3)$, it was infeasible for multiple real applications, where $n$ could be large. This stimulates researchers to propose the approximate spectral clustering (ASC). However, most of ASC methods assumed that the number of clusters $k$ was known. In practice, manual setting of $k$ could be subjective or time consuming. The proposed algorithm has two relevance metrics for estimating $k$ in two vital steps of ASC. One for selecting the eigenvectors spanning the embedding space, and the other to discover the number of clusters in that space. The algorithm used a growing neural gas (GNG) approximation, GNG is superior in preserving input data topology. The experimental setup demonstrates the efficiency of the proposed algorithm and its ability to compete with similar methods where $k$ was set manually.