A Novel Composite Graph Neural Network

Graph neural networks (GNNs) have achieved great success in many fields due to their powerful capabilities of processing graph-structured data. However, most GNNs can only be applied to scenarios where graphs are known, but real-world data are often noisy or even do not have available graph structur...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transaction on neural networks and learning systems 2024-10, Vol.35 (10), p.13411-13425
Hauptverfasser:	Liu, Zhaogeng, Yang, Jielong, Zhong, Xionghu, Wang, Wenwu, Chen, Hechang, Chang, Yi
Format:	Artikel
Sprache:	eng
Schlagworte:	Aggregates Composite graph (C-graph) Graph neural networks graph neural networks (GNNs) Learning (artificial intelligence) Learning systems Noise measurement Prediction methods Robustness sample graph tree-based feature graph
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!