# Towards Principled Disentanglement for Domain Generalization

arXiv: https://arxiv.org/abs/2111.13839 · HTML: https://mlsanity.com/paper/2111.13839/

## Key facts

- Cited by 91 papers in the map (data through 14 Oct 2026).
- Builds on 64 of its 88 references that are in the map.
- First posted on arXiv 27 Nov 2021.

## Builds on (most cited first, 30 of 64)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018)
- [Causal inference using invariant prediction: identification and confidence intervals](https://mlsanity.com/paper/1501.01332/) (2015)
- [Generalizing to Unseen Domains via Adversarial Data Augmentation](https://mlsanity.com/paper/1805.12018/) (2018)
- [Domain Generalization by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1903.06864/) (2019)
- [Learning the Difference that Makes a Difference with Counterfactually-Augmented Data](https://mlsanity.com/paper/1909.12434/) (2019)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [Fairness Without Demographics in Repeated Loss Minimization](https://mlsanity.com/paper/1806.08010/) (2018)

## Built on by (most cited first, 30 of 91)

- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [NICO++: Towards Better Benchmarking for Domain Generalization](https://mlsanity.com/paper/2204.08040/) (2022)
- [Sparse Mixture-of-Experts are Domain Generalizable Learners](https://mlsanity.com/paper/2206.04046/) (2022)
- [OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling](https://mlsanity.com/paper/2309.12659/) (2023)
- [AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation](https://mlsanity.com/paper/2304.12566/) (2023)
- [Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning](https://mlsanity.com/paper/2211.14666/) (2022)
- [Free Lunch for Domain Adversarial Training: Environment Label Smoothing](https://mlsanity.com/paper/2302.00194/) (2023)
- [Out-of-Distribution Representation Learning for Time Series Classification](https://mlsanity.com/paper/2209.07027/) (2022)
- [Unbiased Faster R-CNN for Single-source Domain Generalized Object Detection](https://mlsanity.com/paper/2405.15225/) (2024)
- [ALOFT: A Lightweight MLP-like Architecture with Dynamic Low-frequency Transform for Domain Generalization](https://mlsanity.com/paper/2303.11674/) (2023)
- [Flatness-Aware Minimization for Domain Generalization](https://mlsanity.com/paper/2307.11108/) (2023)
- [Exploring Transformer Backbones for Heterogeneous Treatment Effect Estimation](https://mlsanity.com/paper/2202.01336/) (2022)
- [Learning Invariant Visual Representations for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2206.00415/) (2022)
- [DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization](https://mlsanity.com/paper/2308.02282/) (2023)
- [DGMamba: Domain Generalization via Generalized State Space Model](https://mlsanity.com/paper/2404.07794/) (2024)
- [Unknown Prompt, the only Lacuna: Unveiling CLIP's Potential for Open Domain Generalization](https://mlsanity.com/paper/2404.00710/) (2024)
- [Automatic Data Augmentation via Invariance-Constrained Learning](https://mlsanity.com/paper/2209.15031/) (2022)
- [Rethinking Domain Generalization: Discriminability and Generalizability](https://mlsanity.com/paper/2309.16483/) (2023)
- [Domain-Specific Risk Minimization for Out-of-Distribution Generalization](https://mlsanity.com/paper/2208.08661/) (2022)
- [Learning Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity](https://mlsanity.com/paper/2311.12267/) (2023)
- [Modality-Agnostic Debiasing for Single Domain Generalization](https://mlsanity.com/paper/2303.07123/) (2023)
- [Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issues](https://mlsanity.com/paper/2303.08106/) (2023)
- [V2X-DGW: Domain Generalization for Multi-agent Perception under Adverse Weather Conditions](https://mlsanity.com/paper/2403.11371/) (2024)
- [Towards Fair Disentangled Online Learning for Changing Environments](https://mlsanity.com/paper/2306.01007/) (2023)
- [Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learning](https://mlsanity.com/paper/2502.10691/) (2025)
- [Diverse Target and Contribution Scheduling for Domain Generalization](https://mlsanity.com/paper/2309.16460/) (2023)
- [Activate and Reject: Towards Safe Domain Generalization under Category Shift](https://mlsanity.com/paper/2310.04724/) (2023)
- [A Survey on Domain Generalization for Medical Image Analysis](https://mlsanity.com/paper/2402.05035/) (2024)
- [Recurrent Aligned Network for Generalized Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2403.05810/) (2024)
- [Gradient-Guided Annealing for Domain Generalization](https://mlsanity.com/paper/2502.20162/) (2025)

## Abstract (arXiv)

A fundamental challenge for machine learning models is generalizing to out-of-distribution (OOD) data, in part due to spurious correlations. To tackle this challenge, we first formalize the OOD generalization problem as constrained optimization, called Disentanglement-constrained Domain Generalization (DDG). We relax this non-trivial constrained optimization problem to a tractable form with finite-dimensional parameterization and empirical approximation. Then a theoretical analysis of the extent to which the above transformations deviates from the original problem is provided. Based on the transformation, we propose a primal-dual algorithm for joint representation disentanglement and domain generalization. In contrast to traditional approaches based on domain adversarial training and domain labels, DDG jointly learns semantic and variation encoders for disentanglement, enabling flexible manipulation and augmentation on training data. DDG aims to learn intrinsic representations of semantic concepts that are invariant to nuisance factors and generalizable across domains. Comprehensive experiments on popular benchmarks show that DDG can achieve competitive OOD performance and uncover interpretable salient structures within data.