Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.28931 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914432925302784 |
|---|---|
| author | Karmi, Shira Avidan, Galia Raviv, Tammy Riklin |
| author_facet | Karmi, Shira Avidan, Galia Raviv, Tammy Riklin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_28931 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Decoding Functional Networks for Visual Categories via GNNs Karmi, Shira Avidan, Galia Raviv, Tammy Riklin Computer Vision and Pattern Recognition 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. |
| title | Decoding Functional Networks for Visual Categories via GNNs |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.28931 |