Beyond Homophily and Homogeneity Assumption: Relation-Based Frequency Adaptive Graph Neural Networks

Graph neural networks (GNNs) have been playing important roles in various graph-related tasks. However, most existing GNNs are based on the assumption of homophily, so they cannot be directly generalized to heterophily settings where connected nodes may have different features and class labels. More...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transaction on neural networks and learning systems 2024-06, Vol.35 (6), p.8497-8509
Hauptverfasser:	Wu, Lirong, Lin, Haitao, Hu, Bozhen, Tan, Cheng, Gao, Zhangyang, Liu, Zicheng, Li, Stan Z.
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptation models Electronic mail Feature extraction Graph neural networks Graph neural networks (GNNs) Graphical representations Graphs Heterogeneity heterogeneous graph heterophily graph Homogeneity Kernel Message passing Neural networks Nodes relation learning Signal processing Task analysis Theoretical analysis Transforms
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!