Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Decoding Functional Networks for Visual Categories via GNNs

Shira Karmi, Galia Avidan, Tammy Riklin Raviv

Abstract

Understanding how large-scale brain networks represent visual categories is fundamental to linking perception and cortical organization. Using high-resolution 7T fMRI from the Natural Scenes Dataset, we construct parcel-level functional graphs and train a signed Graph Neural Network that models both positive and negative interactions, with a sparse edge mask and class-specific saliency. The model accurately decodes category-specific functional connectivity states (sports, food, vehicles) and reveals reproducible, biologically meaningful subnetworks along the ventral and dorsal visual pathways. This framework bridges machine learning and neuroscience by extending voxel-level category selectivity to a connectivity-based representation of visual processing.

Decoding Functional Networks for Visual Categories via GNNs

Abstract

Understanding how large-scale brain networks represent visual categories is fundamental to linking perception and cortical organization. Using high-resolution 7T fMRI from the Natural Scenes Dataset, we construct parcel-level functional graphs and train a signed Graph Neural Network that models both positive and negative interactions, with a sparse edge mask and class-specific saliency. The model accurately decodes category-specific functional connectivity states (sports, food, vehicles) and reveals reproducible, biologically meaningful subnetworks along the ventral and dorsal visual pathways. This framework bridges machine learning and neuroscience by extending voxel-level category selectivity to a connectivity-based representation of visual processing.

Paper Structure

This paper contains 23 sections, 8 equations, 6 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Methods
  3. Dataset
  4. Preprocessing
  5. Connectivity Matrix Construction
  6. Signed GNN Architecture
  7. Explainability
  8. Experiments
  9. Hemisphere Selection
  10. Setup and Data Splits
  11. Training Protocol
  12. Evaluation
  13. Results
  14. Latent-Space Organization
  15. Quantitative Evaluation
  16. ...and 8 more sections

Figures (6)

  • Figure 2: t-SNE progression of graph embeddings across training. Clusters emerge for sports (blue), food (red), and vehicle (green), showing the signed GNN gradually disentangles category-selective connectivity patterns.
  • Figure 3: Top-weighted parcels for sports, food, and vehicle. Warmer colors denote higher relevance from the learned mask and saliency.
  • Figure : (a) Sport
  • Figure : (a) Sport
  • Figure : (b) Food
  • ...and 1 more figures