Research on Clustering Performance of Sparse Subspace Clustering

TL;DR

This paper examines how different methods of constructing coefficient and affinity matrices affect the clustering accuracy and stability in sparse subspace clustering, highlighting the importance of these factors for high-dimensional data analysis.

Contribution

It systematically compares various combinations of coefficient and affinity matrix construction methods to evaluate their impact on clustering performance.

Findings

Both coefficient and affinity matrices significantly influence clustering results.

Certain combinations yield better accuracy and stability.

Developing more stable algorithms remains an open challenge.

Abstract

Recently, sparse subspace clustering has been a valid tool to deal with high-dimensional data. There are two essential steps in the framework of sparse subspace clustering. One is solving the coefficient matrix of data, and the other is constructing the affinity matrix from the coefficient matrix, which is applied to the spectral clustering. This paper investigates the factors which affect clustering performance from both clustering accuracy and stability of the approaches based on existing algorithms. We select four methods to solve the coefficient matrix and use four different ways to construct a similarity matrix for each coefficient matrix. Then we compare the clustering performance of different combinations on three datasets. The experimental results indicate that both the coefficient matrix and affinity matrix have a huge influence on clustering performance and how to develop a stable and valid algorithm still needs to be studied.