Limitless stability for Graph Convolutional Networks

This work establishes rigorous, novel and widely applicable stability guarantees and transferability bounds for graph convolutional networks -- without reference to any underlying limit object or statistical distribution. Crucially, utilized graph-shift operators (GSOs) are not necessarily assumed t...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-09
1. Verfasser:	Koke, Christian
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Granulation Graphs Mathematical analysis Networks Norms Operators (mathematics) Perturbation Stability
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!