Tracing Network Evolution Using the PARAFAC2 Model

TL;DR

This paper introduces the use of the PARAFAC2 tensor factorization model to analyze and trace the evolution of dynamic networks, such as brain connectivity, without assuming static structures, demonstrated through simulations and fMRI data.

Contribution

The paper applies the PARAFAC2 model to capture and analyze time-evolving networks in neuroimaging data, providing a new approach for dynamic network analysis.

Findings

PARAFAC2 successfully reveals underlying networks and their dynamics in simulated data.

The model effectively traces the evolution of functional connectivity in brain fMRI data.

Demonstrates promising results in understanding complex time-varying systems.

Abstract

Characterizing time-evolving networks is a challenging task, but it is crucial for understanding the dynamic behavior of complex systems such as the brain. For instance, how spatial networks of functional connectivity in the brain evolve during a task is not well-understood. A traditional approach in neuroimaging data analysis is to make simplifications through the assumption of static spatial networks. In this paper, without assuming static networks in time and/or space, we arrange the temporal data as a higher-order tensor and use a tensor factorization model called PARAFAC2 to capture underlying patterns (spatial networks) in time-evolving data and their evolution. Numerical experiments on simulated data demonstrate that PARAFAC2 can successfully reveal the underlying networks and their dynamics. We also show the promising performance of the model in terms of tracing the evolution of task-related functional connectivity in the brain through the analysis of functional magnetic resonance imaging data.