A Review of Nonnegative Matrix Factorization Methods for Clustering
Machine Learning
2015-08-31 v2 Machine Learning
Numerical Analysis
Abstract
Nonnegative Matrix Factorization (NMF) was first introduced as a low-rank matrix approximation technique, and has enjoyed a wide area of applications. Although NMF does not seem related to the clustering problem at first, it was shown that they are closely linked. In this report, we provide a gentle introduction to clustering and NMF before reviewing the theoretical relationship between them. We then explore several NMF variants, namely Sparse NMF, Projective NMF, Nonnegative Spectral Clustering and Cluster-NMF, along with their clustering interpretations.
Keywords
Cite
@article{arxiv.1507.03194,
title = {A Review of Nonnegative Matrix Factorization Methods for Clustering},
author = {Ali Caner Türkmen},
journal= {arXiv preprint arXiv:1507.03194},
year = {2015}
}