BrainMAP: Learning Multiple Activation Pathways in Brain Networks
BrainMAP learns multiple brain network activation pathways via sequential models and Mixture-of-Experts, improving fMRI analysis and interpretability.
Published Apr 11, 20252 citationsPaper ↗
Only vote on papers you've read. Sign in with GitHub to vote.
BrainMAP pairs sequential long-range brain paths with MoE routing to address multi-pathway learning, earning praise as a timely structural fix, though reservations remain that arbitrary region ordering, missing ablations, and unverified pathway separation leave its biological…
Abstract
Functional Magnetic Resonance Image (fMRI) is commonly employed to study human brain activity, since it offers insight into the relationship between functional fluctuations and human behavior. To enhance analysis and comprehension of brain activity, Graph Neural Networks (GNNs) have been widely applied to the analysis of functional connectivities (FC) derived from fMRI data, due to their ability to capture the synergistic interactions among brain regions. However, in the human brain, performing complex tasks typically involves the activation of certain pathways, which could be represented as paths across graphs. As such, conventional GNNs struggle to learn from these pathways due to the long-range dependencies of multiple pathways. To address these challenges, we introduce a novel framework BrainMAP to learn multiple pathways in brain networks. BrainMAP leverages sequential models to identify long-range correlations among sequentialized brain regions and incorporates an aggregation module based on Mixture of Experts (MoE) to learn from multiple pathways. Our comprehensive experiments highlight BrainMAP's superior performance. Furthermore, our framework enables explanatory analyses of crucial brain regions involved in tasks.