# Learning Discrete and Continuous Factors of Data via Alternating Disentanglement

arXiv: https://arxiv.org/abs/1905.09432 · HTML: https://mlsanity.com/paper/1905.09432/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2019.

## Built on by (most cited first, 23 of 23)

- [Tutorial on amortized optimization](https://mlsanity.com/paper/2202.00665/) (2022)
- [Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation](https://mlsanity.com/paper/2108.07668/) (2021)
- [Where and What? Examining Interpretable Disentangled Representations](https://mlsanity.com/paper/2104.05622/) (2021)
- [Commutative Lie Group VAE for Disentanglement Learning](https://mlsanity.com/paper/2106.03375/) (2021)
- [Latent Traversals in Generative Models as Potential Flows](https://mlsanity.com/paper/2304.12944/) (2023)
- [Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement](https://mlsanity.com/paper/2102.05185/) (2021)
- [Lost in Latent Space: Disentangled Models and the Challenge of Combinatorial Generalisation](https://mlsanity.com/paper/2204.02283/) (2022)
- [Flow Factorized Representation Learning](https://mlsanity.com/paper/2309.13167/) (2023)
- [Raven's Progressive Matrices Completion with Latent Gaussian Process Priors](https://mlsanity.com/paper/2103.12045/) (2021)
- [CFASL: Composite Factor-Aligned Symmetry Learning for Disentanglement in Variational AutoEncoder](https://mlsanity.com/paper/2401.08897/) (2024)
- [Unsupervised Representation Learning from Sparse Transformation Analysis](https://mlsanity.com/paper/2410.05564/) (2024)
- [DEFT: Distilling Entangled Factors by Preventing Information Diffusion](https://mlsanity.com/paper/2102.03986/) (2021)
- [DOT-VAE: Disentangling One Factor at a Time](https://mlsanity.com/paper/2210.10920/) (2022)
- [Reliable Federated Disentangling Network for Non-IID Domain Feature](https://mlsanity.com/paper/2301.12798/) (2023)
- [Variantional autoencoder with decremental information bottleneck for disentanglement](https://mlsanity.com/paper/2303.12959/) (2023)
- [FREEDOM: Target Label & Source Data & Domain Information-Free Multi-Source Domain Adaptation for Unsupervised Personalization](https://mlsanity.com/paper/2307.02493/) (2023)
- [Learning Disentangled Discrete Representations](https://mlsanity.com/paper/2307.14151/) (2023)
- [How Video Meetings Change Your Expression](https://mlsanity.com/paper/2406.00955/) (2024)
- [Uniform Transformation: Refining Latent Representation in Variational Autoencoders](https://mlsanity.com/paper/2407.02681/) (2024)
- [Inference-InfoGAN: Inference Independence via Embedding Orthogonal Basis Expansion](https://mlsanity.com/paper/2110.00788/) (2021)
- [Multiple Invertible and Partial-Equivariant Function for Latent Vector Transformation to Enhance Disentanglement in VAEs](https://mlsanity.com/paper/2502.03740/) (2025)
- [What We Don't C: Manifold Disentanglement for Structured Discovery](https://mlsanity.com/paper/2511.09433/) (2025)
- [Neurocircuitry-Inspired Hierarchical Graph Causal Attention Networks for Explainable Depression Identification](https://mlsanity.com/paper/2511.17622/) (2025)

## Abstract (arXiv)

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 β-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 https://github.com/snu-mllab/DisentanglementICML19.