title: Isolating Sources of Disentanglement in Variational Autoencoders

authors: Ricky T. Q. Chen, Xuechen Li, Roger Grosse, David Duvenaud

year: 2019

doi: 10.48550/arXiv.1802.04942

zotero: zotero://select/items/@chenIsolatingSourcesDisentanglement2019

---

Isolating Sources of Disentanglement in Variational Autoencoders

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.