Semi-supervised Symmetric Non-negative Matrix Factorization with Low-Rank Tensor Representation

TL;DR

This paper introduces a novel semi-supervised symmetric non-negative matrix factorization method that leverages low-rank tensor representations to globally enhance clustering performance, outperforming previous local-constraint approaches.

Contribution

It proposes a new low-rank tensor-based semi-supervised SNMF model that globally integrates pairwise constraints and similarity matrices for improved clustering.

Findings

The proposed method outperforms existing SNMF techniques in clustering tasks.

The tensor-based approach effectively captures global low-rank structures.

Experimental results demonstrate significant improvements in clustering quality.

Abstract

Semi-supervised symmetric non-negative matrix factorization (SNMF) utilizes the available supervisory information (usually in the form of pairwise constraints) to improve the clustering ability of SNMF. The previous methods introduce the pairwise constraints from the local perspective, i.e., they either directly refine the similarity matrix element-wisely or restrain the distance of the decomposed vectors in pairs according to the pairwise constraints, which overlook the global perspective, i.e., in the ideal case, the pairwise constraint matrix and the ideal similarity matrix possess the same low-rank structure. To this end, we first propose a novel semi-supervised SNMF model by seeking low-rank representation for the tensor synthesized by the pairwise constraint matrix and a similarity matrix obtained by the product of the embedding matrix and its transpose, which could strengthen those two matrices simultaneously from a global perspective. We then propose an enhanced SNMF model, making the embedding matrix tailored to the above tensor low-rank representation. We finally refine the similarity matrix by the strengthened pairwise constraints. We repeat the above steps to continuously boost the similarity matrix and pairwise constraint matrix, leading to a high-quality embedding matrix. Extensive experiments substantiate the superiority of our method. The code is available at https://github.com/JinaLeejnl/TSNMF.