#mini-batching

Timed test

1 question · 1 min · score and explanations at the end

Q 1 / 1Score 0 / 0

Shuffle questions

How does PyTorch Geometric put several graphs of different sizes into one mini-batch?

As one big graph with a block-diagonal adjacency matrix and a batch vector1
By padding every graph with dummy nodes up to the size of the largest graph2
By resampling the graphs so that each one has the same number of nodes3
By stacking the dense adjacency matrices into one tensor of shape $(B, n, n)$ 4

Keys: 1–9 select · Enter check / next