SyncAI.news, a Varaisys broadcasting
On the Informativeness of Structural Stability Bounds for GNNs: GINs versus GATs
AG

Alan Gany, Paul Landrier, Bogdan Cautis, Laks V. S. Lakshmanan, Silviu Maniu

· 1 min read

ResearcharXiv cs.LG

On the Informativeness of Structural Stability Bounds for GNNs: GINs versus GATs

arXiv:2611.25603v1 Announce Type: new 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 under deterministic edge perturbations that need not be small, and compare each with such a perturbation-independent diameter bound. For GINs, we characterize exactly when the stability bound is tighter, through a condition linking perturbation size, depth and maximum degree; it holds with a wide margin on Cora, but fails beyond a few layers on the low-degree MUTAG graphs. For GATv1, the bound is never tighter, which calls for analyses based on attention masses.

Original source

This story was published by arXiv cs.LG and written by Alan Gany, Paul Landrier, Bogdan Cautis, Laks V. S. Lakshmanan, Silviu Maniu. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News