# Weakly Supervised Disentanglement by Pairwise Similarities

arXiv: https://arxiv.org/abs/1906.01044 · HTML: https://mlsanity.com/paper/1906.01044/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2019.

## Built on by (most cited first, 22 of 22)

- [GlanceNets: Interpretabile, Leak-proof Concept-based Models](https://mlsanity.com/paper/2205.15612/) (2022)
- [Identifiability Results for Multimodal Contrastive Learning](https://mlsanity.com/paper/2303.09166/) (2023)
- [On Causally Disentangled Representations](https://mlsanity.com/paper/2112.05746/) (2021)
- [Learning Disentangled Representations of Negation and Uncertainty](https://mlsanity.com/paper/2204.00511/) (2022)
- [Simple Disentanglement of Style and Content in Visual Representations](https://mlsanity.com/paper/2302.09795/) (2023)
- [Review of Disentanglement Approaches for Medical Applications -- Towards Solving the Gordian Knot of Generative Models in Healthcare](https://mlsanity.com/paper/2203.11132/) (2022)
- [C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder](https://mlsanity.com/paper/2310.17325/) (2023)
- [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)
- [Leveraging Relational Information for Learning Weakly Disentangled Representations](https://mlsanity.com/paper/2205.10056/) (2022)
- [Retrieval-based Disentangled Representation Learning with Natural Language Supervision](https://mlsanity.com/paper/2212.07699/) (2022)
- [Disentangled Variational Autoencoder for Emotion Recognition in Conversations](https://mlsanity.com/paper/2305.14071/) (2023)
- [SC-VAE: Sparse Coding-based Variational Autoencoder with Learned ISTA](https://mlsanity.com/paper/2303.16666/) (2023)
- [SW-VAE: Weakly Supervised Learn Disentangled Representation Via Latent Factor Swapping](https://mlsanity.com/paper/2209.10623/) (2022)
- [Right for the Right Latent Factors: Debiasing Generative Models via Disentanglement](https://mlsanity.com/paper/2202.00391/) (2022)
- [Out of Distribution Reasoning by Weakly-Supervised Disentangled Logic Variational Autoencoder](https://mlsanity.com/paper/2210.09959/) (2022)
- [Affinity-VAE: incorporating prior knowledge in representation learning from scientific images](https://mlsanity.com/paper/2209.04517/) (2022)
- [3D-IDS: Doubly Disentangled Dynamic Intrusion Detection](https://mlsanity.com/paper/2307.11079/) (2023)
- [Enhancing Interpretability in Generative Modeling: Statistically Disentangled Latent Spaces Guided by Generative Factors in Scientific Datasets](https://mlsanity.com/paper/2507.00298/) (2025)
- [Generative Modeling Helps Weak Supervision (and Vice Versa)](https://mlsanity.com/paper/2203.12023/) (2022)
- [Modular Representations for Weak Disentanglement](https://mlsanity.com/paper/2209.05336/) (2022)
- [RACH-Space: Reconstructing Adaptive Convex Hull Space with Applications in Weak Supervision](https://mlsanity.com/paper/2307.04870/) (2023)

## Abstract (arXiv)

Recently, researches related to unsupervised disentanglement learning with deep generative models have gained substantial popularity. However, without introducing supervision, there is no guarantee that the factors of interest can be successfully recovered. Motivated by a real-world problem, we propose a setting where the user introduces weak supervision by providing similarities between instances based on a factor to be disentangled. The similarity is provided as either a binary (yes/no) or a real-valued label describing whether a pair of instances are similar or not. We propose a new method for weakly supervised disentanglement of latent variables within the framework of Variational Autoencoder. Experimental results demonstrate that utilizing weak supervision improves the performance of the disentanglement method substantially.