Skip to content
ml-recall

#normalisation

2 questions from Graph Neural Networks

Timed test

2 questions · 2 min · score and explanations at the end

Take a test
Q 1 / 2Score 0 / 0

Question 1: Single choice

mediumAI-checkedGraph Neural Networks

A GCN layer computes σ(D~−1/2A~D~−1/2HW)\sigma(\tilde D^{-1/2}\tilde A\tilde D^{-1/2} H W), where A~=A+I\tilde A = A + I is the adjacency matrix with self-loops and D~\tilde D its diagonal degree matrix, D~ii=∑jA~ij\tilde D_{ii} = \sum_j \tilde A_{ij}. What would go wrong if it computed σ(A~HW)\sigma(\tilde A H W), without the degree normalisation?

Choose one option