# Learning Disentangled Representations with Semi-Supervised Deep Generative Models

arXiv: https://arxiv.org/abs/1706.00400 · HTML: https://mlsanity.com/paper/1706.00400/

## Key facts

- Cited by 72 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jun 2017.

## Built on by (most cited first, 30 of 72)

- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2212.08698/) (2022)
- [No Representation Rules Them All in Category Discovery](https://mlsanity.com/paper/2311.17055/) (2023)
- [Learning Disentangled Representations in the Imaging Domain](https://mlsanity.com/paper/2108.12043/) (2021)
- [World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges](https://mlsanity.com/paper/2301.05832/) (2023)
- [Towards Explaining Distribution Shifts](https://mlsanity.com/paper/2210.10275/) (2022)
- [Source-free unsupervised domain adaptation for cross-modality abdominal multi-organ segmentation](https://mlsanity.com/paper/2111.12221/) (2021)
- [MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularization](https://mlsanity.com/paper/2203.14316/) (2022)
- [Learning Multimodal VAEs through Mutual Supervision](https://mlsanity.com/paper/2106.12570/) (2021)
- [Lifelong Teacher-Student Network Learning](https://mlsanity.com/paper/2107.04689/) (2021)
- [Action2video: Generating Videos of Human 3D Actions](https://mlsanity.com/paper/2111.06925/) (2021)
- [Moment Matching Deep Contrastive Latent Variable Models](https://mlsanity.com/paper/2202.10560/) (2022)
- [Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement](https://mlsanity.com/paper/2102.05185/) (2021)
- [Lifelong Mixture of Variational Autoencoders](https://mlsanity.com/paper/2107.04694/) (2021)
- [ULLER: A Unified Language for Learning and Reasoning](https://mlsanity.com/paper/2405.00532/) (2024)
- [Semi-Supervised Disentanglement of Class-Related and Class-Independent Factors in VAE](https://mlsanity.com/paper/2102.00892/) (2021)
- [Disentanglement Learning for Variational Autoencoders Applied to Audio-Visual Speech Enhancement](https://mlsanity.com/paper/2105.08970/) (2021)
- [Learning Proposals for Probabilistic Programs with Inference Combinators](https://mlsanity.com/paper/2103.00668/) (2021)
- [VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Experts](https://mlsanity.com/paper/2103.07292/) (2021)
- [DisUnknown: Distilling Unknown Factors for Disentanglement Learning](https://mlsanity.com/paper/2109.08090/) (2021)
- [Improving VAE-based Representation Learning](https://mlsanity.com/paper/2205.14539/) (2022)
- [Smoothness Analysis for Probabilistic Programs with Application to Optimised Variational Inference](https://mlsanity.com/paper/2208.10530/) (2022)
- [Separating common from salient patterns with Contrastive Representation Learning](https://mlsanity.com/paper/2402.11928/) (2024)
- [Joint Diffusion models in Continual Learning](https://mlsanity.com/paper/2411.08224/) (2024)
- [Semi-supervised source localization in reverberant environments with deep generative modeling](https://mlsanity.com/paper/2101.10636/) (2021)
- [EXoN: EXplainable encoder Network](https://mlsanity.com/paper/2105.10867/) (2021)
- [Hamming Similarity and Graph Laplacians for Class Partitioning and Adversarial Image Detection](https://mlsanity.com/paper/2305.01808/) (2023)
- [Disentanglement Learning via Topology](https://mlsanity.com/paper/2308.12696/) (2023)
- [Towards Controllable Time Series Generation](https://mlsanity.com/paper/2403.03698/) (2024)
- [Diffusion-Refined VQA Annotations for Semi-Supervised Gaze Following](https://mlsanity.com/paper/2406.02774/) (2024)

## Abstract (arXiv)

Variational autoencoders (VAEs) learn representations of data by jointly training a probabilistic encoder and decoder network. Typically these models encode all features of the data into a single variable. Here we are interested in learning disentangled representations that encode distinct aspects of the data into separate variables. We propose to learn such representations using model architectures that generalise from standard VAEs, employing a general graphical model structure in the encoder and decoder. This allows us to train partially-specified models that make relatively strong assumptions about a subset of interpretable variables and rely on the flexibility of neural networks to learn representations for the remaining variables. We further define a general objective for semi-supervised learning in this model class, which can be approximated using an importance sampling procedure. We evaluate our framework's ability to learn disentangled representations, both by qualitative exploration of its generative capacity, and quantitative evaluation of its discriminative ability on a variety of models and datasets.