# Gated Variational AutoEncoders: Incorporating Weak Supervision to Encourage Disentanglement

arXiv: https://arxiv.org/abs/1911.06443 · HTML: https://mlsanity.com/paper/1911.06443/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2019.

## Built on by (most cited first, 6 of 6)

- [Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations](https://mlsanity.com/paper/2112.02290/) (2021)
- [Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models](https://mlsanity.com/paper/2407.18999/) (2024)
- [VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Experts](https://mlsanity.com/paper/2103.07292/) (2021)
- [SKILL-IL: Disentangling Skill and Knowledge in Multitask Imitation Learning](https://mlsanity.com/paper/2205.03130/) (2022)
- [Adversarial Disentanglement by Backpropagation with Physics-Informed Variational Autoencoder](https://mlsanity.com/paper/2506.13658/) (2025)
- [Imitation Learning Based on Disentangled Representation Learning of Behavioral Characteristics](https://mlsanity.com/paper/2509.04737/) (2025)

## Abstract (arXiv)

Variational AutoEncoders (VAEs) provide a means to generate representational latent embeddings. Previous research has highlighted the benefits of achieving representations that are disentangled, particularly for downstream tasks. However, there is some debate about how to encourage disentanglement with VAEs and evidence indicates that existing implementations of VAEs do not achieve disentanglement consistently. The evaluation of how well a VAE's latent space has been disentangled is often evaluated against our subjective expectations of which attributes should be disentangled for a given problem. Therefore, by definition, we already have domain knowledge of what should be achieved and yet we use unsupervised approaches to achieve it. We propose a weakly-supervised approach that incorporates any available domain knowledge into the training process to form a Gated-VAE. The process involves partitioning the representational embedding and gating backpropagation. All partitions are utilised on the forward pass but gradients are backpropagated through different partitions according to selected image/target pairings. The approach can be used to modify existing VAE models such as beta-VAE, InfoVAE and DIP-VAE-II. Experiments demonstrate that using gated backpropagation, latent factors are represented in their intended partition. The approach is applied to images of faces for the purpose of disentangling head-pose from facial expression. Quantitative metrics show that using Gated-VAE improves average disentanglement, completeness and informativeness, as compared with un-gated implementations. Qualitative assessment of latent traversals demonstrate its disentanglement of head-pose from expression, even when only weak/noisy supervision is available.