Discriminatively Constrained Semi-supervised Multi-view Nonnegative Matrix Factorization with Graph Regularization

TL;DR

This paper introduces a novel semi-supervised multi-view NMF method that enhances cluster discrimination and feature alignment using discriminative weighting and graph regularization, improving multi-view clustering performance.

Contribution

The paper proposes DCS^2MVNMF, integrating discriminative weighting and graph regularization for better multi-view clustering, with a new feature normalization and optimization scheme.

Findings

Effective in enhancing inter-class distinction.

Improves multi-view clustering accuracy.

Validated on real-world datasets.

Abstract

In recent years, semi-supervised multi-view nonnegative matrix factorization (MVNMF) algorithms have achieved promising performances for multi-view clustering. While most of semi-supervised MVNMFs have failed to effectively consider discriminative information among clusters and feature alignment from multiple views simultaneously. In this paper, a novel Discriminatively Constrained Semi-Supervised Multi-View Nonnegative Matrix Factorization (DCS^2MVNMF) is proposed. Specifically, a discriminative weighting matrix is introduced for the auxiliary matrix of each view, which enhances the inter-class distinction. Meanwhile, a new graph regularization is constructed with the label and geometrical information. In addition, we design a new feature scale normalization strategy to align the multiple views and complete the corresponding iterative optimization schemes. Extensive experiments conducted on several real world multi-view datasets have demonstrated the effectiveness of the proposed method.