Aug 2026
MD-VAE: Concepts embedded variational autoencoder with multiple decoders
The Multi-Decoder Concept Embedding Variational Autoencoder (MD-VAE), which enhances latent space interpretability by learning distinct latent variables through multiple decoders and can improve the prediction performance of VAE while discovering differences between different concepts.
Zi-Tu Liu, Yue Liu, Shuang Li et al.
· Applied intelligence (Boston... · 0 citations