/gnn

An implementation of the Graph Neural Networks for the Cora dataset

Primary LanguagePython

An implementation of the Graph Convolution Networks (GCN) for the Cora dataset

Visual

Data source: Cora dataset link

The macro F1 plot of the result

macroF1

The loss plot of the result

loss

The testing result:

  1. macro F1: 0.8537
  2. Loss: 0.4782

Reference

  1. Kipf, Thomas N., and Max Welling. "Semi-supervised classification with graph convolutional networks." arXiv preprint arXiv:1609.02907 (2016).
  2. McCallum, Andrew Kachites, et al. "Automating the construction of internet portals with machine learning." Information Retrieval 3.2 (2000): 127-163.