.png){kind=icon}
.png){kind=icon}
Return
MD-VAE: Concepts embedded variational autoencoder with multiple decoders
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-026-07435-3.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Variational autoencoders (VAE) construct latent space by optimizing the prior distribution and posterior distribution of the model. Existing methods exhibit limited interpretability during the construction of the latent space, which hinders their capacity to effectively capture the disentangled representation of concepts. To construct an interpretable latent space, we propose the Multi-Decoder Concept Embedding Variational Autoencoder (MD-VAE), which enhances latent space interpretability by learning distinct latent variables through multiple decoders. Firstly, the MD-VAE model learns prior concept by training on generated data that represent this concept, thereby embedding the prior into the latent space. Subsequently, we propose a variational inference framework utilizing multiple decoders. In this framework, encoders map multiple latent variables into the latent space, and each corresponding set of latent variables is reconstructed by its dedicated decoder. On the basis of this, a theoretical derivation of variational lower bound of multiple decodes is combined with variation method to obtain the optimal model parameter estimates. Finally, experiments on MNIST, FashionMNIST, COIL20, and USPS datasets show that MD-VAE can improve the prediction performance of VAE while discovering differences between different concepts.
Keywords:
Variational autoencoder
Disentangled representation
Deep learning interpretability
Journal
IF:
3.5
Papers:
7.5K
Citations:
1.7W
View more organizations