Nonnegative Matrix Factorization for Signal and Data Analytics: Identifiability, Algorithms, and Applications
Preprint
Abstract
Nonnegative matrix factorization (NMF) has become a workhorse for signal and data analytics, triggered by its model parsimony and interpretability. Perhaps a bit surprisingly, the understanding to its model identifiability---the major reason behind the interpretability in many applications such as topic mining and hyperspectral imaging---had been rather limited until recent years. Beginning from the 2010s, the identifiability research of NMF has progressed considerably: Many interesting and important results have been discovered by the signal processing (SP) and machine learning (ML) communities. NMF identifiability has a great impact on many aspects in practice, such as ill-posed formulation avoidance and performance-guaranteed algorithm design. On the other hand, there is no tutorial paper that introduces NMF from an identifiability viewpoint. In this paper, we aim at filling this gap by offering a comprehensive and deep tutorial on model identifiability of NMF as well as the connections to algorithms and applications. This tutorial will help researchers and graduate students grasp the essence and insights of NMF, thereby avoiding typical `pitfalls' that are often times due to unidentifiable NMF formulations. This paper will also help practitioners pick/design suitable factorization tools for their own problems.Keywords
All Related Versions
This publication has 48 references indexed in Scilit:
- Robust volume minimization-based matrix factorization via alternating optimization2016
- Robustness Analysis of Structured Matrix Factorization via Self-Dictionary Mixed-Norm OptimizationIEEE Signal Processing Letters, 2015
- Self-Dictionary Sparse Regression for Hyperspectral Unmixing: Greedy Pursuit and Pure Pixel Search Are RelatedIEEE Journal of Selected Topics in Signal Processing, 2015
- Blind source separation of positive and partially correlated dataSignal Processing, 2005
- Metagenes and molecular pattern discovery using matrix factorizationProceedings of the National Academy of Sciences, 2004
- The successive projections algorithm for variable selection in spectroscopic multicomponent analysisChemometrics and Intelligent Laboratory Systems, 2001
- Learning the parts of objects by non-negative matrix factorizationNature, 1999
- Positive matrix factorization: A non‐negative factor model with optimal utilization of error estimates of data valuesEnvironmetrics, 1994
- Minimum-volume transforms for remotely sensed dataIEEE Transactions on Geoscience and Remote Sensing, 1994
- The nonnegative rank factorizations of nonnegative matricesLinear Algebra and its Applications, 1984