Graph Oversampling Method Based on Graph Latent Representation Distribution Learning

In the real world, many graph datasets suffer from class imbalance issues, typically manifesting at the node, edge, and graph levels. Common oversampling-based methods for addressing graph-level imbalance often lead to model overfitting due to a lack of sample diversity. To address this issue, a gra...

Celý popis

Podrobná bibliografie

Hlavní autor:	REN Bo, DONG Minggang, YU Yang, LU Xianrui
Médium:	Artigo
Jazyk:	Chinês
Vydáno:	Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press 2025-07-01
Edice:	Jisuanji kexue yu tansuo
Témata:	long-tail problem; variational graph auto-encoder; graph latent representation; generative adversarial network
On-line přístup:	http://fcst.ceaj.org/fileup/1673-9418/PDF/2407119.pdf
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!