Skip to content

Mathew0553/BNGNN

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 

Repository files navigation

0.BN-GNN
Python implementation for "Deep reinforcement learning guided graph neural networks for brain network analysis"

1.Overview
data.tar: Compression of three public datasets.
/model/dqn.py: Realize the meta-policy module in BN-GNN.
/model/gnn.py: Realize the network building module and the GNN module in BN-GNN.
main.py: Entry file of BN-GNN.

2.Example
python main.py

3.Requirements
python=3.6.7
pytorch=1.4.0
cudnn=7.6.5
numpy=1.19.5
scipy=1.2.1
deepwalk=1.0.3

4.Baselines
DeepWalk: "Deepwalk: Online learning of social representations"
Node2Vec: "Node2vec: Scalable feature learning for networks"
GCN: "Semi-supervised classification with graph convolutional networks"
GAT: "Graph attention networks"
GraphSAGE: "Inductive representation learning on large graphs"
FastGCN: "FastGCN: Fast learning with graph convolutional networks via importance sampling"
PR-GNN: "Pooling regularized graph neural network for fmri biomarker analysis"
GNEA: "GNEA: A graph neural network with ELM aggregator for brain network classification"
Hi-GCN: "Hi-GCN: A hierarchical graph convolution network for graph embedding learning of brain network and brain disorders prediction"
SDBN: "Structural deep brain network mining"

5.Public Datasets
ADHD-fMRI & HI-fMRI & GD-fMRI
"Task sensitive feature exploration and learning for multitask graph classification"
"A whole brain fMRI atlas generated via spatially constrained spectral clustering"

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%