Topic: "dense-array"
mahnoorsheikh16/Node-Classification-with-Graph-Neural-Networks
Evaluation of multiple graph neural network models—GCN, GAT, GraphSAGE, MPNN and DGI—for node classification on graph-structured data. Preprocessing includes feature normalization and adjacency-matrix regularization, and an ensemble of model predictions boosts performance. The best ensemble achieves 83.47% test accuracy.
Language: Jupyter Notebook - Size: 286 KB - Last synced at: about 1 month ago - Pushed at: about 2 months ago - Stars: 1 - Forks: 0
Related Topics
deep-graph-infomax
1
deep-infomax
1
deep-learning
1
deep-neural-networks
1
ensemble-learning
1
feature-normalization
1
gcn-architecture
1
graph-attention-network
1
graph-neural-networks
1
graphsage
1
loss-functions
1
mpnn-model
1
node-classification
1
pytorch-implementation
1
pytorch-tensors
1
regularization
1
relu-layer
1
softmax-function
1