Fast Approximated Multiple Kernel K-Means

Jun Wang

doi:10.1109/TKDE.2023.3340743

Return

Fast Approximated Multiple Kernel K-Means

2024-11-01

PRE

Xinwang Liu (Xinwang Liu)

Wei Zhang

En Zhu

Xinzhong Zhu

DOI：10.1109/TKDE.2023.3340743

Original

Original request for help

Save

Abstract

En 中文

Multiple Kernel Clustering (MKC) has emerged as a prominent research domain in recent decades due to its capacity to exploit diverse information from multiple views by learning an optimal kernel. Despite the successes achieved by various MKC methods, a significant challenge lies in the computational complexity associated with generating a consensus partition from the optimal kernel matrix, typically of size n x n , where n represents the number of samples. This computational bottleneck restricts the practical applicability of these methods when confronted with large-scale datasets. Furthermore, certain existing MKC algorithms derive the consensus partition matrix by fusing all base partitions. However, this fusion process may inadvertently overlook critical information embedded in individual base kernels, potentially leading to inferior clustering performance. In light of these challenges, we introduce an innovative and efficient multiple kernel k -means approach, denoted as FAMKKM. Notably, FAMKKM incorporates two approximated partition matrices instead of the original individual partition matric for each base kernel. This strategic substitution significantly reduces computational complexity. Additionally, FAMKKM leverages the original kernel information to guide the fusion of all base partitions, thereby enhancing the quality of the resulting consensus partition matrix. Finally, we substantiate the efficacy and efficiency of the proposed FAMKKM through extensive experiments conducted on six benchmark datasets. Our results demonstrate its superiority over state-of-the-art methods.

Keywords:

Kernel

Clustering algorithms

Partitioning algorithms

Computational complexity

Optimization

Linear programming

Matrix decomposition

Multi-view clustering

partition learning

multiple kernel k -means

data fusion