A State-Space Approach to Dynamic Nonnegative Matrix Factorization

TL;DR

This paper introduces a novel state-space framework for dynamic nonnegative matrix factorization (NMF) that models temporal dependencies in time series data, outperforming existing methods in accuracy and efficiency.

Contribution

It proposes a probabilistic state-space model for dynamic NMF using N-VAR, with a maximum-likelihood estimation framework and a Kalman-like update, advancing temporal modeling in NMF.

Findings

D-NMF significantly outperforms static NMF in simulations.

The approach surpasses state-of-the-art methods like hidden Markov models.

It requires less memory and computational power.

Abstract

Nonnegative matrix factorization (NMF) has been actively investigated and used in a wide range of problems in the past decade. A significant amount of attention has been given to develop NMF algorithms that are suitable to model time series with strong temporal dependencies. In this paper, we propose a novel state-space approach to perform dynamic NMF (D-NMF). In the proposed probabilistic framework, the NMF coefficients act as the state variables and their dynamics are modeled using a multi-lag nonnegative vector autoregressive (N-VAR) model within the process equation. We use expectation maximization and propose a maximum-likelihood estimation framework to estimate the basis matrix and the N-VAR model parameters. Interestingly, the N-VAR model parameters are obtained by simply applying NMF. Moreover, we derive a maximum a posteriori estimate of the state variables (i.e., the NMF coefficients) that is based on a prediction step and an update step, similarly to the Kalman filter. We illustrate the benefits of the proposed approach using different numerical simulations where D-NMF significantly outperforms its static counterpart. Experimental results for three different applications show that the proposed approach outperforms two state-of-the-art NMF approaches that exploit temporal dependencies, namely a nonnegative hidden Markov model and a frame stacking approach, while it requires less memory and computational power.