Learning Discrete and Continuous Factors of Data via Alternating Disentanglement

By Yeonwoo Jeong, Hyun Oh Song. 2019

49 citations recorded by the source corpus.

We address the problem of unsupervised disentanglement of discrete and continuous explanatory factors of data. We first show a simple procedure for minimizing the total correlation of the continuous latent variables without having to use a discriminator network or perform importance sampling, via cascading the information flow in the $\beta$-vae framework. Furthermore, we propose a method which avoids offloading the entire burden of jointly modeling the continuous and discrete factors to the variational encoder by employing a separate discrete inference procedure. This leads to an interesting alternating minimization problem which switches between finding the most likely discrete configuration given the continuous factors and updating the variational encoder based on the computed discrete factors. Experiments show that the proposed method clearly disentangles discrete factors and significantly outperforms current disentanglement methods based on the disentanglement score and inference network classification score. The source code is available at this https URL.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Fei Ye
2. Adrian G. Bors
3. Xiao Liu
4. Zhongqin Wu
5. Yuxiang Wei
6. Wangmeng Zuo
7. Zhilong Ji
8. Yuan Gao

Citations in the corpus

• Learning latent representations across multiple data domains using Lifelong VAEGAN (2020, background): “VAE framework in order to learn a meaningful representation of the data by imposing a large penalty on the Kullback-Leibler (KL) divergence term [7,17,25] or on the total correlation latent variables [12,20,28,30]. These approaches perform well on independent and identically distributed data samples”
• Learning joint latent representations based on information maximization (2021, methodology): “Recently, various methods have been developed to induce disentangled representations without sacrificing the reconstruction quality [20,21].”
• Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation (2021, methodology): “Variational Autoencoder (VAE) [26] and Generative Adversarial Networks (GAN) [12], many disentanglement methods [6, 7, 11, 15, 17, 25, 32, 38, 48] have been proposed.”