On Addressing the Limitations of Graph Neural Networks

On Addressing the Limitations of Graph Neural Networks

This report gives a summary of two problems about graph convolutional networks (GCNs): over-smoothing and heterophily challenges, and outlines future directions to explore.

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-07
1. Verfasser: Luan, Sitao
Format: Artikel
Sprache:eng
Schlagworte:
Artificial neural networks
Graph neural networks
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This report gives a summary of two problems about graph convolutional networks (GCNs): over-smoothing and heterophily challenges, and outlines future directions to explore.
ISSN:2331-8422