Local kernel alignment based multi-view clustering using extreme learning machine

Abstract

Abstract A similarity or dissimilarity measure, such as the Euclidean distance, is crucial to discriminative clustering algorithms. These measures used to calculate pairwise similarities between samples rely on data representations in a feature space. However, discriminative clustering fails if the samples in a feature space are linearly inseparable. This problem can be solved by performing a nonlinear data transformation into a high dimensional feature space, which can increase the probability of the linear separability of the samples within the transformed feature space and simplify the associated data structure. Mercer kernels, which are constructed using such a nonlinear data transformation, have been widely used in clustering tasks. Extreme learning machine (ELM) is a new method that exhibits promising clustering performance owing to its universal approximation capability, easy parameter selection, explicit feature mapping process, and excellent feature representation capability. This study proposes an ELM based multi-view learning approach with different views generated by ELM random feature mapping with respect to different hidden-layer nodes, and exploits the properties of these views. Experiments show that better clustering results can be obtained by combining these views together compared with the corresponding ELM-based single-view clustering methods and the traditional algorithms which are performed in the feature space of the original data. Moreover, local kernel alignment property is widespread in these views. This alignment helps the clustering algorithm focus on closer sample pairs. This study also proposes an ELM based multiple kernel clustering algorithm with local kernel alignment maximization. The proposed algorithm is experimentally demonstrated on 10 single-view benchmark datasets and yields superior clustering performance when compared with the state-of-the-art multi-view clustering methods in recent literatures. Thus, the effectiveness and superiority of maximizing local kernel alignment on those views constructed by the proposed method are verified.