Skip to content

Code associated with paper "Multimodal Graph Coarsening for Interpretable, MRI-Based Graph Neural Network"

Notifications You must be signed in to change notification settings

isebenius/MM-GNN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 

Repository files navigation

MM-GNN

Repo with code associated with paper "Multimodal Graph Coarsening for Interpretable, MRI-Based Graph Neural Network"

MMSAG.py and MMTopK.py provide implementations of the multimodal SAGPooling and TopK pooling layers described in the paper for M=2 input modalities.

MMGNN.py provides code for the model architecture used to obtain the results on the COBRE case/control dataset, accessible here.

The model can be integrated into a standard PyTorch training script using data formatted with the PairData function provided by PyTorch Geometric.

About

Code associated with paper "Multimodal Graph Coarsening for Interpretable, MRI-Based Graph Neural Network"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages