# Dual Swap Disentangling

arXiv: https://arxiv.org/abs/1805.10583 · HTML: https://mlsanity.com/paper/1805.10583/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2018.

## Built on by (most cited first, 12 of 12)

- [Factorizing Knowledge in Neural Networks](https://mlsanity.com/paper/2207.03337/) (2022)
- [Disentanglement and Generalization Under Correlation Shifts](https://mlsanity.com/paper/2112.14754/) (2021)
- [DisUnknown: Distilling Unknown Factors for Disentanglement Learning](https://mlsanity.com/paper/2109.08090/) (2021)
- [Disentanglement Learning via Topology](https://mlsanity.com/paper/2308.12696/) (2023)
- [Do-Operation Guided Causal Representation Learning with Reduced Supervision Strength](https://mlsanity.com/paper/2206.01802/) (2022)
- [SW-VAE: Weakly Supervised Learn Disentangled Representation Via Latent Factor Swapping](https://mlsanity.com/paper/2209.10623/) (2022)
- [Shadow Datasets, New challenging datasets for Causal Representation Learning](https://mlsanity.com/paper/2308.05707/) (2023)
- [Weakly Supervised Disentangled Representation for Goal-conditioned Reinforcement Learning](https://mlsanity.com/paper/2202.13624/) (2022)
- [Variational Transfer Learning using Cross-Domain Latent Modulation](https://mlsanity.com/paper/2205.15523/) (2022)
- [Weakly Supervised Recovery of Semantic Attributes](https://mlsanity.com/paper/2103.11888/) (2021)
- [ProtoVAE: Prototypical Networks for Unsupervised Disentanglement](https://mlsanity.com/paper/2305.09092/) (2023)
- [XFACTORS: Disentangled Information Bottleneck via Contrastive Supervision](https://mlsanity.com/paper/2601.21688/) (2026)

## Abstract (arXiv)

Learning interpretable disentangled representations is a crucial yet challenging task. In this paper, we propose a weakly semi-supervised method, termed as Dual Swap Disentangling (DSD), for disentangling using both labeled and unlabeled data. Unlike conventional weakly supervised methods that rely on full annotations on the group of samples, we require only limited annotations on paired samples that indicate their shared attribute like the color. Our model takes the form of a dual autoencoder structure. To achieve disentangling using the labeled pairs, we follow a "encoding-swap-decoding" process, where we first swap the parts of their encodings corresponding to the shared attribute and then decode the obtained hybrid codes to reconstruct the original input pairs. For unlabeled pairs, we follow the "encoding-swap-decoding" process twice on designated encoding parts and enforce the final outputs to approximate the input pairs. By isolating parts of the encoding and swapping them back and forth, we impose the dimension-wise modularity and portability of the encodings of the unlabeled samples, which implicitly encourages disentangling under the guidance of labeled pairs. This dual swap mechanism, tailored for semi-supervised setting, turns out to be very effective. Experiments on image datasets from a wide domain show that our model yields state-of-the-art disentangling performances.