# Learning Disentangled Semantic Representation for Domain Adaptation

arXiv: https://arxiv.org/abs/2012.11807 · HTML: https://mlsanity.com/paper/2012.11807/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2020.

## Built on by (most cited first, 30 of 55)

- [Domain Adaptation via Prompt Learning](https://mlsanity.com/paper/2202.06687/) (2022)
- [Towards Principled Disentanglement for Domain Generalization](https://mlsanity.com/paper/2111.13839/) (2021)
- [Vector-Decomposed Disentanglement for Domain-Invariant Object Detection](https://mlsanity.com/paper/2108.06685/) (2021)
- [Self-Supervised Learning Disentangled Group Representation as Feature](https://mlsanity.com/paper/2110.15255/) (2021)
- [Transporting Causal Mechanisms for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2107.11055/) (2021)
- [Subspace Identification for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2310.04723/) (2023)
- [Graph Domain Adaptation: A Generative View](https://mlsanity.com/paper/2106.07482/) (2021)
- [ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2106.10812/) (2021)
- [Learning Domain Invariant Representations for Generalizable Person Re-Identification](https://mlsanity.com/paper/2103.15890/) (2021)
- [Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective](https://mlsanity.com/paper/2208.07365/) (2022)
- [Transferable Time-Series Forecasting under Causal Conditional Shift](https://mlsanity.com/paper/2111.03422/) (2021)
- [Modeling Techniques for Machine Learning Fairness: A Survey](https://mlsanity.com/paper/2111.03015/) (2021)
- [Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement](https://mlsanity.com/paper/2201.01929/) (2022)
- [Partial Identifiability for Domain Adaptation](https://mlsanity.com/paper/2306.06510/) (2023)
- [Graph Domain Adaptation: Challenges, Progress and Prospects](https://mlsanity.com/paper/2402.00904/) (2024)
- [Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment](https://mlsanity.com/paper/2110.06448/) (2021)
- [An Unsupervised Domain Adaptation Model based on Dual-module Adversarial Training](https://mlsanity.com/paper/2112.15555/) (2021)
- [Learning Disentangled Representations for Time Series](https://mlsanity.com/paper/2105.08179/) (2021)
- [Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts](https://mlsanity.com/paper/2211.04393/) (2022)
- [Emo-DNA: Emotion Decoupling and Alignment Learning for Cross-Corpus Speech Emotion Recognition](https://mlsanity.com/paper/2308.02190/) (2023)
- [COSMo: CLIP Talks on Open-Set Multi-Target Domain Adaptation](https://mlsanity.com/paper/2409.00397/) (2024)
- [Time-Series Domain Adaptation via Sparse Associative Structure Alignment: Learning Invariance and Variance](https://mlsanity.com/paper/2205.03554/) (2022)
- [Distortion-Disentangled Contrastive Learning](https://mlsanity.com/paper/2303.05066/) (2023)
- [INSURE: An Information Theory Inspired Disentanglement and Purification Model for Domain Generalization](https://mlsanity.com/paper/2309.04063/) (2023)
- [Learning Transferable Conceptual Prototypes for Interpretable Unsupervised Domain Adaptation](https://mlsanity.com/paper/2310.08071/) (2023)
- [Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learning](https://mlsanity.com/paper/2503.00639/) (2025)
- [Preserving Clusters in Prompt Learning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2506.11493/) (2025)
- [Disentanglement by Cyclic Reconstruction](https://mlsanity.com/paper/2112.12980/) (2021)
- [Discriminative Radial Domain Adaptation](https://mlsanity.com/paper/2301.00383/) (2023)
- [Where and How to Attack? A Causality-Inspired Recipe for Generating Counterfactual Adversarial Examples](https://mlsanity.com/paper/2312.13628/) (2023)

## Abstract (arXiv)

Domain adaptation is an important but challenging task. Most of the existing domain adaptation methods struggle to extract the domain-invariant representation on the feature space with entangling domain information and semantic information. Different from previous efforts on the entangled feature space, we aim to extract the domain invariant semantic information in the latent disentangled semantic representation (DSR) of the data. In DSR, we assume the data generation process is controlled by two independent sets of variables, i.e., the semantic latent variables and the domain latent variables. Under the above assumption, we employ a variational auto-encoder to reconstruct the semantic latent variables and domain latent variables behind the data. We further devise a dual adversarial network to disentangle these two sets of reconstructed latent variables. The disentangled semantic latent variables are finally adapted across the domains. Experimental studies testify that our model yields state-of-the-art performance on several domain adaptation benchmark datasets.