Deep matrix factorizations

TL;DR

Deep matrix factorization extends traditional low-rank approximation techniques by enabling hierarchical feature extraction, inspired by deep learning, and has demonstrated outstanding performance in unsupervised tasks.

Contribution

This paper provides a comprehensive review of deep matrix factorization models, algorithms, applications, and discusses future research directions.

Findings

Deep MF achieves superior performance on unsupervised tasks.

It effectively extracts hierarchical features from complex data.

The paper discusses theoretical aspects and potential research perspectives.

Abstract

Constrained low-rank matrix approximations have been known for decades as powerful linear dimensionality reduction techniques to be able to extract the information contained in large data sets in a relevant way. However, such low-rank approaches are unable to mine complex, interleaved features that underlie hierarchical semantics. Recently, deep matrix factorization (deep MF) was introduced to deal with the extraction of several layers of features and has been shown to reach outstanding performances on unsupervised tasks. Deep MF was motivated by the success of deep learning, as it is conceptually close to some neural networks paradigms. In this paper, we present the main models, algorithms, and applications of deep MF through a comprehensive literature review. We also discuss theoretical questions and perspectives of research.