.png){kind=icon}
.png){kind=icon}
Return
Cloud-VAE: Variational autoencoder with concepts emb e dde d
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2023.109530.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Variational Autoencoder (VAE) has been widely and successfully used in learning coherent latent repre-sentation of data. However, the lack of interpretability in the latent space constructed by the VAE under the prior distribution is still an urgent problem. This paper proposes a VAE with understandable concept embedding named Cloud-VAE, which constructs interpretable latent space by disentangling the latent variables and considering their uncertainty based on cloud model. Firstly, cloud model-based clustering algorithm cast initial constraint of latent space into a prior distribution of concept which can be em-bedded into the latent space of the VAE to disentangle the latent variables. Secondly, reparameterization trick based on forward cloud transformation algorithm is designed to estimate the latent space concept by increasing the randomness of latent variables. Furthermore, variational lower bound of Cloud-VAE is derived to guide the training process to construct concepts of latent space, realizing the mutual mapping between latent space and concept space. Finally, experimental results on 6 benchmark datasets show that Cloud-VAE has good clustering and reconstruction performance, which can explicitly explain the aggre-gation process of the model and discover more interpretable disentangled representations.& COPY; 2023 Elsevier Ltd. All rights reserved.
Keywords:
Variational autoencoder
Disentangled representation
Concept embedded
Cloud Model
Deep Learning Interpretability
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W