DynDepNet: Learning Time-Varying Dependency Structures from fMRI Data via Dynamic Graph Structure Learning

TL;DR

DynDepNet is a novel approach that learns dynamic brain connectivity graphs from fMRI data, improving prediction accuracy and aligning with neuroscience findings.

Contribution

It introduces a method to learn time-varying dependency structures in fMRI data tailored for downstream tasks, addressing static graph limitations.

Findings

Achieves state-of-the-art accuracy in sex classification from fMRI data.

Outperforms baseline models by approximately 8 and 6 percentage points.

Reveals brain regions consistent with neuroscience literature.

Abstract

Graph neural networks (GNNs) have demonstrated success in learning representations of brain graphs derived from functional magnetic resonance imaging (fMRI) data. However, existing GNN methods assume brain graphs are static over time and the graph adjacency matrix is known prior to model training. These assumptions contradict evidence that brain graphs are time-varying with a connectivity structure that depends on the choice of functional connectivity measure. Incorrectly representing fMRI data with noisy brain graphs can adversely affect GNN performance. To address this, we propose DynDepNet, a novel method for learning the optimal time-varying dependency structure of fMRI data induced by downstream prediction tasks. Experiments on real-world fMRI datasets, for the task of sex classification, demonstrate that DynDepNet achieves state-of-the-art results, outperforming the best baseline in terms of accuracy by approximately 8 and 6 percentage points, respectively. Furthermore, analysis of the learned dynamic graphs reveals prediction-related brain regions consistent with existing neuroscience literature.