FPED: A Functional-Network Prior-Guided Mixture-of-Experts Framework for Interpretable Brain Decoding

TL;DR

FPED is a novel brain decoding framework that models functional brain networks as experts, enabling interpretable visual reconstruction from fMRI with competitive performance and meaningful neuroscientific insights.

Contribution

The paper introduces FPED, a mixture-of-experts model guided by neurobiological priors, for structured, interpretable brain decoding of visual semantics from fMRI data.

Findings

Achieves competitive semantic reconstruction with 0.68B parameters.

Reveals meaningful correspondence between brain networks and semantic processing.

Provides transparent interpretability of neural decoding models.

Abstract

Visual image reconstruction from functional Magnetic Resonance Imaging (fMRI) is a fundamental task in brain decoding, providing a crucial pathway for understanding human perceptual mechanisms and developing advanced brain-computer interfaces (BCIs). However, most current methods simply flatten fMRI signals from localized visual cortices into one-dimensional (1D) vectors, mapping them directly into latent spaces such as that of Contrastive Language-Image Pre-training (CLIP). This paradigm not only disrupts the inherent network topology of the brain-leading to limited neuroscientific interpretability-but also overlooks the synergistic contributions of other distributed functional networks in processing high-level visual semantics. To address these limitations, we propose FPED, a Functional-Network Prior-Guided Mixture of Experts (MoE) framework for interpretable brain decoding. FPED explicitly models different functional brain networks as specialized experts and employs adaptive routing to capture their complementary contributions to visual semantic understanding. Unlike conventional homogeneous decoding paradigms, our framework incorporates neurobiologically grounded priors to enable structured and interpretable network-level representation learning. Experimental results demonstrate that FPED achieves highly competitive semantic reconstruction performance with only 0.68B parameters. The learned routing dynamics reveal biologically meaningful correspondence between functional brain networks and modality-specific semantic processing, providing transparent neuroscientific interpretability. This suggests that brain network-aware expert modeling is a promising direction for bridging neural decoding and biologically inspired artificial intelligence.