We decompose the evidence lower bound to show the existence of a term
measuring the total correlation between latent variables. We use this to
motivate our $\beta$-TCVAE (Total Correlation Variational Autoencoder), a
refinement of the state-of-the-art $\beta$-VAE objective for learning
disentangled representations, requiring no additional hyperparameters during
training. We further propose a principled classifier-free measure of
disentanglement called the mutual information gap (MIG). We perform extensive
quantitative and qualitative experiments, in both restricted and non-restricted
settings, and show a strong relation between total correlation and
disentanglement, when the latent variables model is trained using our
framework.

我们提出了一种基于 Total Correlation Variational Autoencoder 的无监督学习方法，用以生成 disentangled representations，并介绍了一种分类器无关的 disentanglement 度量，称为 mutual information gap (MIG)。通过对 restricted 和 non-restricted 实验结果的定量和定性分析，我们展示了 latent variables model 的 total correlation 和 disentanglement 之间的强关联关系。