Back to Models
DIPVAE
đ DisentanglementDisentangled Inferred Prior VAE
RNA
VAE that learns a factorial prior to encourage disentanglement
Publications
Variational Inference of Disentangled Latent Concepts from Unlabeled Observations
Complexity
â
â
â
complexInterpretability
â
â
â
highArchitecture
DIPVAE
Latent Dim
10
Factorial Prior Learning
DIPVAE encourages disentanglement by regularizing the covariance of the aggregate posterior to be diagonal (factorized) with full VAE reconstruction
Main Idea
Encourage factorial posterior by matching aggregate posterior covariance to identity matrix while reconstructing
Key Components
Encoder
Maps to factorial latent space
Covariance Regularization
Regularizes Cov[q(z)] to be diagonal
Factorial Prior
Encourages independence across dimensions
Type I/II Variants
Different regularization strategies
Decoder
Reconstructs from factorial latents
Mathematical Formulation
L = ELBO + Îť*||Cov_q(z) - I||_F²; XĚ = Decoder(z)
Loss Functions
DIPVAE Loss
Reconstruction + KL + Îť*Covariance Penalty
Data Flow
Data â Encoder â Factorial Latents â Decoder â Reconstruction
Architecture Details
Architecture Type
VAE with Factorial Prior Learning (VAE Architecture)
Input/Output Types
single-cell â reconstruction
Key Layers
EncoderCovarianceRegularizerDecoder
Frameworks
PyTorch
Tags
vaedisentanglementfactorial-priorgenerativerna