A perturbation-recovery generative autoencoder for heterogeneous graphs with attributes missing

Abstract Heterogeneous graphs are widely employed in applications such as social networks, recommendation systems, and bioinformatics. However, node attributes in real-world heterogeneous graphs are often missing or corrupted, which substantially degrades representation quality and downstream task p...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Quan Wang, Xinru Shao, Xiaodi Huang
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	Nature Portfolio 2026-03-01
Schriftenreihe:	Scientific Reports
Schlagworte:	Heterogeneous graph Attribute missing Graph autoencoder Adversarial training
Online-Zugang:	https://doi.org/10.1038/s41598-026-44190-4
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!