.png){kind=icon}
.png){kind=icon}
Return
Dirichlet Variational Autoencoder
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2020.107514.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper proposes Dirichlet Variational Autoencoder (DirVAE) using a Dirichlet prior. To infer the parameters of DirVAE, we utilize the stochastic gradient method by approximating the inverse cumulative distribution function of the Gamma distribution, which is a component of the Dirichlet distribution. This approximation on a new prior led an investigation on the component collapsing, and DirVAE revealed that the component collapsing originates from two problem sources: decoder weight collapsing and latent value collapsing. The experimental results show that 1) DirVAE generates the result with the best log-likelihood compared to the baselines; 2) DirVAE produces more interpretable latent values with no collapsing issues which the baselines suffer from; 3) the latent representation from DirVAE achieves the best classification accuracy in the (semi-)supervised classification tasks on MNIST, OMNIGLOT, COIL-20, SVHN, and CIFAR-10 compared to the baseline VAEs; and 4) the DirVAE augmented topic models show better performances in most cases. (C) 2020 Elsevier Ltd. All rights reserved.
Keywords:
Representation learning
Variational autoencoder
Deep generative model
Multi-modal latent representation
Component collapse
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.