Abstract: Stability bounds for graph neural networks limit how much node representations can drift when the graph changes, but they are rarely compared with the simplest alternative: a bound on the distance between any two outputs, whatever the graph. We derive structural stability bounds for Graph Isomorphism Networks (GINs) and single-head GATv1 networks
[…]
Content was trimmed to protect the source. Please visit the original article for the full text.
Read the original article:
On the Informativeness of Structural Stability Bounds for GNNs: GINs versus GATs
