A Deep Latent Variable Framework for Jointly Modeling Missingness, Measurement Error, and Heterogeneity
A unified probabilistic framework that jointly addresses missing data, measurement error, and population heterogeneity utilizing deep latent variable representation is proposed that integrates a novel hierarchical tree-routed variational autoencoder with pattern-aware latent representations and calibration-based denoising.
Yasin Khadem Charvadeh, Grace Y. Yi, Mithat Gönen et al.
· 0 citations