# Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift

arXiv: https://arxiv.org/abs/2003.04475 · HTML: https://mlsanity.com/paper/2003.04475/

## Key facts

- Cited by 125 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Mar 2020.

## Built on by (most cited first, 30 of 125)

- [Leveraging Unlabeled Data to Predict Out-of-Distribution Performance](https://mlsanity.com/paper/2201.04234/) (2022)
- [Invariant Information Bottleneck for Domain Generalization](https://mlsanity.com/paper/2106.06333/) (2021)
- [A Prototype-Oriented Framework for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2110.12024/) (2021)
- [Domain Invariant Representation Learning with Domain Density Transformations](https://mlsanity.com/paper/2102.05082/) (2021)
- [Optimal Representations for Covariate Shift](https://mlsanity.com/paper/2201.00057/) (2021)
- [Domain Adversarial Neural Networks for Domain Generalization: When It Works and How to Improve](https://mlsanity.com/paper/2102.03924/) (2021)
- [Structural Re-weighting Improves Graph Domain Adaptation](https://mlsanity.com/paper/2306.03221/) (2023)
- [Online Adaptation to Label Distribution Shift](https://mlsanity.com/paper/2107.04520/) (2021)
- [Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate](https://mlsanity.com/paper/2107.13469/) (2021)
- [Near-Optimal Linear Regression under Distribution Shift](https://mlsanity.com/paper/2106.12108/) (2021)
- [Simple and Asymmetric Graph Contrastive Learning without Augmentations](https://mlsanity.com/paper/2310.18884/) (2023)
- [Subspace Identification for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2310.04723/) (2023)
- [Quantifying and Improving Transferability in Domain Generalization](https://mlsanity.com/paper/2106.03632/) (2021)
- [KL Guided Domain Adaptation](https://mlsanity.com/paper/2106.07780/) (2021)
- [Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments](https://mlsanity.com/paper/2106.09913/) (2021)
- [RLSbench: Domain Adaptation Under Relaxed Label Shift](https://mlsanity.com/paper/2302.03020/) (2023)
- [Gradual Domain Adaptation without Indexed Intermediate Domains](https://mlsanity.com/paper/2207.04587/) (2022)
- [Pairwise Alignment Improves Graph Domain Adaptation](https://mlsanity.com/paper/2403.01092/) (2024)
- [Aggregating From Multiple Target-Shifted Sources](https://mlsanity.com/paper/2105.04051/) (2021)
- [Any-Shift Prompting for Generalization over Distributions](https://mlsanity.com/paper/2402.10099/) (2024)
- [Transferring Fairness under Distribution Shifts via Fair Consistency Regularization](https://mlsanity.com/paper/2206.12796/) (2022)
- [Your Data Is Not Perfect: Towards Cross-Domain Out-of-Distribution Detection in Class-Imbalanced Data](https://mlsanity.com/paper/2412.06284/) (2024)
- [Efficient Conditionally Invariant Representation Learning](https://mlsanity.com/paper/2212.08645/) (2022)
- [Domain Generalization under Conditional and Label Shifts via Variational Bayesian Inference](https://mlsanity.com/paper/2107.10931/) (2021)
- [Variational Disentanglement for Domain Generalization](https://mlsanity.com/paper/2109.05826/) (2021)
- [Mapping conditional distributions for domain adaptation under generalized target shift](https://mlsanity.com/paper/2110.15057/) (2021)
- [Gradual Domain Adaptation: Theory and Algorithms](https://mlsanity.com/paper/2310.13852/) (2023)
- [Combating Label Distribution Shift for Active Domain Adaptation](https://mlsanity.com/paper/2208.06604/) (2022)
- [A Data Fusion Framework for Multi-Domain Morality Learning](https://mlsanity.com/paper/2304.02144/) (2023)
- [Controlling Directions Orthogonal to a Classifier](https://mlsanity.com/paper/2201.11259/) (2022)

## Abstract (arXiv)

Adversarial learning has demonstrated good performance in the unsupervised domain adaptation setting, by learning domain-invariant representations. However, recent work has shown limitations of this approach when label distributions differ between the source and target domains. In this paper, we propose a new assumption, generalized label shift (GLS), to improve robustness against mismatched label distributions. GLS states that, conditioned on the label, there exists a representation of the input that is invariant between the source and target domains. Under GLS, we provide theoretical guarantees on the transfer performance of any classifier. We also devise necessary and sufficient conditions for GLS to hold, by using an estimation of the relative class weights between domains and an appropriate reweighting of samples. Our weight estimation method could be straightforwardly and generically applied in existing domain adaptation (DA) algorithms that learn domain-invariant representations, with small computational overhead. In particular, we modify three DA algorithms, JAN, DANN and CDAN, and evaluate their performance on standard and artificial DA tasks. Our algorithms outperform the base versions, with vast improvements for large label distribution mismatches. Our code is available at https://tinyurl.com/y585xt6j.