CaEGCN: Cross-Attention Fusion Based Enhanced Graph Convolutional Network for Clustering

With the powerful learning ability of deep convolutional networks, deep clustering methods can extract the most discriminative information from individual data and produce more satisfactory clustering results. However, existing deep clustering methods usually ignore the relationship between the data...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on knowledge and data engineering 2023-04, Vol.35 (4), p.3471-3483
Hauptverfasser:	Huo, Guangyu, Zhang, Yong, Gao, Junbin, Wang, Boyue, Hu, Yongli, Yin, Baocai
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Clustering Clustering methods Coders Cross-attention fusion mechanism Data mining deep clustering Deep learning graph convolutional network Image reconstruction Image segmentation Modules Representations Smoothing methods Task analysis
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!