GAHIB: graph attention VAE with a hyperbolic information bottleneck for biologically structured single-cell representations

Current single-cell RNA-sequencing (scRNA-seq) variational autoencoders (VAEs) usually emphasise local cell graph structure, hyperbolic latent geometry, or bottleneck compression separately, yet these biases are rarely evaluated together in one evidence-gated representation model. We present GAHIB (...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Zeyu Fu, Jiawei Fu, Xiaoxia Wang, Yiyao Liu, Tianfei Ran
Formato:	Artigo
Idioma:	Inglês
Publicado em:	Frontiers Media S.A. 2026-06-01
coleção:	Frontiers in Genetics
Assuntos:	graph attention network hyperbolic geometry information bottleneck representation learning single-cell RNA-seq variational autoencoder
Acesso em linha:	https://www.frontiersin.org/articles/10.3389/fgene.2026.1863100/full
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!