Learning discrete adaptive receptive fields for graph convolutional networks

Different nodes in a graph neighborhood generally yield different importance. In previous work of graph convolutional networks (GCNs), such differences are typically modeled with attention mechanisms. However, as we prove in our paper, soft attention weights suffer from undesired smoothness large ne...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Science China. Information sciences 2023-12, Vol.66 (12), p.222101, Article 222101
Hauptverfasser:	Ma, Xiaojun, Li, Ziyao, Song, Guojie, Shi, Chuan
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Computer Science Graphs Information Systems and Communication Service Neighborhoods Neural networks Nodes Random variables Research Paper Smoothness
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!