首页 > AI前沿 > On the Informativeness of Structural Stability Bounds for GNNs: GINs versus GATs

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

arXiv机器学习 2026-11-19 14:49 15 阅读 查看原文

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 GAT