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...
Spremljeno u:
| Glavni autori: | , , |
|---|---|
| Format: | Artigo |
| Jezik: | Inglês |
| Izdano: |
Nature Portfolio
2026-03-01
|
| Serija: | Scientific Reports |
| Teme: | |
| Online pristup: | https://doi.org/10.1038/s41598-026-44190-4 |
| Oznake: |
Bez oznaka, Budi prvi tko označuje ovaj zapis!
|