Local Sample-weighted Multiple Kernel Clustering with Consensus Discriminative Graph

TL;DR

This paper introduces a novel local sample-weighted multiple kernel clustering method that constructs a consensus discriminative affinity graph, adaptively weights neighbors, and outperforms existing algorithms in local manifold representation.

Contribution

It proposes a new LSWMKC model that adaptively weights neighbors and constructs a consensus affinity graph for improved local clustering performance.

Findings

Outperforms existing kernel and graph-based clustering algorithms.

Constructs a sparse, block-diagonal optimal neighborhood kernel.

Enhances local manifold representation in clustering.

Abstract

Multiple kernel clustering (MKC) is committed to achieving optimal information fusion from a set of base kernels. Constructing precise and local kernel matrices is proved to be of vital significance in applications since the unreliable distant-distance similarity estimation would degrade clustering per-formance. Although existing localized MKC algorithms exhibit improved performance compared to globally-designed competi-tors, most of them widely adopt KNN mechanism to localize kernel matrix by accounting for {\tau} -nearest neighbors. However, such a coarse manner follows an unreasonable strategy that the ranking importance of different neighbors is equal, which is impractical in applications. To alleviate such problems, this paper proposes a novel local sample-weighted multiple kernel clustering (LSWMKC) model. We first construct a consensus discriminative affinity graph in kernel space, revealing the latent local structures. Further, an optimal neighborhood kernel for the learned affinity graph is output with naturally sparse property and clear block diagonal structure. Moreover, LSWMKC im-plicitly optimizes adaptive weights on different neighbors with corresponding samples. Experimental results demonstrate that our LSWMKC possesses better local manifold representation and outperforms existing kernel or graph-based clustering algo-rithms. The source code of LSWMKC can be publicly accessed from https://github.com/liliangnudt/LSWMKC.