AI classification new

aiclusteringsocial-networks

This example is showing how to use a pre-trained Graph Neural Network model to predict node classification. It uses the "Cora" dataset, which is a citation network dataset. The model is trained on the a small subset of 500 nodes of the dataset, and uses the feature vectors extracted from the content of the papers associated with nodes and the cross-citations. This allows it to predict the category of the nodes that the model was not aware of.

You can try and re-train the model on the different parts of the dataset to see the effect it has on the accuracy.