I am trying to understand the following statement taken from the paper Graph Neural Networks: A Review of Methods and Applications (2019).
Standard neural networks like CNNs and RNNs cannot handle the graph input properly in that they stack the feature of nodes by a specific order.
This statement is confusing to me. I have not used CNNs/RNNs for non-Euclidean data before, so perhaps that's where my understanding falls off.
How do CNNs/RNNs stack the feature of nodes by a specific order?