Skip to content
ml-recall

#pyg

5 questions from Graph Neural Networks

Timed test

5 questions · 5 min · score and explanations at the end

Take a test
Q 1 / 5Score 0 / 0

Question 1: Short answer

mediumAI-checkedGraph Neural Networks

Kipf and Welling's two-layer GCN for Cora maps each node's 1,433 bag-of-words features to 16 hidden units and then to the 7 classes. It is built in PyTorch Geometric as GCNConv(1433, 16) followed by GCNConv(16, 7), and each layer keeps PyG's default bias=True, so it has a weight matrix and a bias vector. How many trainable parameters does the model have in total?

a whole number