Showing 2024Show all
3 papers · 1 filter
cs.LG2024
Generalization of Graph Neural Networks is Robust to Model Mismatch
Zhiyang Wang, Juan Cervino, Alejandro Ribeiro
Graph neural networks (GNNs) have demonstrated their effectiveness in various tasks supported by their generalization capabilities. However, the current analysis of GNN generalizat…
eess.SP2024
Generalization of Geometric Graph Neural Networks with Lipschitz Loss Functions
Zhiyang Wang, Juan Cervino, Alejandro Ribeiro
In this paper, we study the generalization capabilities of geometric graph neural networks (GNNs). We consider GNNs over a geometric graph constructed from a finite set of randomly…
cs.LG2024
A Manifold Perspective on the Statistical Generalization of Graph Neural Networks
Zhiyang Wang, Juan Cervino, Alejandro Ribeiro
Graph Neural Networks (GNNs) extend convolutional neural networks to operate on graphs. Despite their impressive performances in various graph learning tasks, the theoretical under…