# Domain Adaptation under Open Set Label Shift

arXiv: https://arxiv.org/abs/2207.13048 · HTML: https://mlsanity.com/paper/2207.13048/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 96 references that are in the map.
- First posted on arXiv 26 Jul 2022.

## Builds on (most cited first, 30 of 48)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [The Implicit Bias of Gradient Descent on Separable Data](https://mlsanity.com/paper/1710.10345/) (2017)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks](https://mlsanity.com/paper/1901.08584/) (2019)
- [Early-Learning Regularization Prevents Memorization of Noisy Labels](https://mlsanity.com/paper/2007.00151/) (2020)
- [Detecting and Correcting for Label Shift with Black Box Predictors](https://mlsanity.com/paper/1802.03916/) (2018)
- [Bridging Theory and Algorithm for Domain Adaptation](https://mlsanity.com/paper/1904.05801/) (2019)
- [Towards Open World Recognition](https://mlsanity.com/paper/1412.5687/) (2014)
- [Positive-Unlabeled Learning with Non-Negative Risk Estimator](https://mlsanity.com/paper/1703.00593/) (2017)
- [Learning from positive and unlabeled data: a survey](https://mlsanity.com/paper/1811.04820/) (2018)
- [To Trust Or Not To Trust A Classifier](https://mlsanity.com/paper/1805.11783/) (2018)
- [Universal Domain Adaptation through Self Supervision](https://mlsanity.com/paper/2002.07953/) (2020)
- [Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2102.03526/) (2021)
- [BREEDS: Benchmarks for Subpopulation Shift](https://mlsanity.com/paper/2008.04859/) (2020)
- [Open Set Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1804.10427/) (2018)
- [Correlation Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1612.01939/) (2016)

## Built on by (most cited first, 30 of 32)

- [Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection](https://mlsanity.com/paper/2306.09158/) (2023)
- [How Does Unlabeled Data Provably Help Out-of-Distribution Detection?](https://mlsanity.com/paper/2402.03502/) (2024)
- [RLSbench: Domain Adaptation Under Relaxed Label Shift](https://mlsanity.com/paper/2302.03020/) (2023)
- [PAC Prediction Sets Under Label Shift](https://mlsanity.com/paper/2310.12964/) (2023)
- [A Short Survey on Importance Weighting for Machine Learning](https://mlsanity.com/paper/2403.10175/) (2024)
- [Handling Out-of-Distribution Data: A Survey](https://mlsanity.com/paper/2507.21160/) (2025)
- [A Closer Look at Novel Class Discovery from the Labeled Set](https://mlsanity.com/paper/2209.09120/) (2022)
- [Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms](https://mlsanity.com/paper/2305.19570/) (2023)
- [Imbalanced Open Set Domain Adaptation via Moving-threshold Estimation and Gradual Alignment](https://mlsanity.com/paper/2303.04393/) (2023)
- [ELSA: Efficient Label Shift Adaptation through the Lens of Semiparametric Models](https://mlsanity.com/paper/2305.19123/) (2023)
- [Generalized Universal Domain Adaptation with Generative Flow Networks](https://mlsanity.com/paper/2305.04466/) (2023)
- [Cross-domain Open-world Discovery](https://mlsanity.com/paper/2406.11422/) (2024)
- [Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift](https://mlsanity.com/paper/2312.03318/) (2023)
- [Out-of-Distribution Detection using Synthetic Data Generation](https://mlsanity.com/paper/2502.03323/) (2025)
- [Positive and Unlabeled Data: Model, Estimation, Inference, and Classification](https://mlsanity.com/paper/2407.09735/) (2024)
- [Federated Learning with Uncertainty-Based Client Clustering for Fleet-Wide Fault Diagnosis](https://mlsanity.com/paper/2304.13275/) (2023)
- [Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies](https://mlsanity.com/paper/2505.22829/) (2025)
- [OASIS: Open-world Adaptive Self-supervised and Imbalanced-aware System](https://mlsanity.com/paper/2508.16656/) (2025)
- [Medix: Out-of-Distribution Detection from Unlabeled Wild Data via Robust Gradient Statistics](https://mlsanity.com/paper/2510.06505/) (2025)
- [Contrastive Novelty-Augmented Learning: Anticipating Outliers with Large Language Models](https://mlsanity.com/paper/2211.15718/) (2022)
- [Generalized Out-of-distribution Fault Diagnosis (GOOFD) via Internal Contrastive Learning](https://mlsanity.com/paper/2306.15266/) (2023)
- [Novel Node Category Detection Under Subpopulation Shift](https://mlsanity.com/paper/2404.01216/) (2024)
- [On the KL-Divergence-based Robust Satisficing Model](https://mlsanity.com/paper/2408.09157/) (2024)
- [Addressing Label Shift in Distributed Learning via Entropy Regularization](https://mlsanity.com/paper/2502.02544/) (2025)
- [Open Set Label Shift with Test Time Out-of-Distribution Reference](https://mlsanity.com/paper/2505.05868/) (2025)
- [Heterogeneous Domain Adaptation with Positive and Unlabeled Data](https://mlsanity.com/paper/2304.07955/) (2023)
- [Semiparametric Learning from Open-Set Label Shift Data](https://mlsanity.com/paper/2509.14522/) (2025)
- [Unsupervised Domain Adaptation for Binary Classification with an Unobservable Source Subpopulation](https://mlsanity.com/paper/2509.20587/) (2025)
- [Information Theory in Open-world Machine Learning Foundations, Frameworks, and Future Direction](https://mlsanity.com/paper/2510.15422/) (2025)
- [Unlocking Out-of-Distribution Generalization in Dynamics through Physics-Guided Augmentation](https://mlsanity.com/paper/2510.24216/) (2025)

## Abstract (arXiv)

We introduce the problem of domain adaptation under Open Set Label Shift (OSLS) where the label distribution can change arbitrarily and a new class may arrive during deployment, but the class-conditional distributions p(x|y) are domain-invariant. OSLS subsumes domain adaptation under label shift and Positive-Unlabeled (PU) learning. The learner's goals here are two-fold: (a) estimate the target label distribution, including the novel class; and (b) learn a target classifier. First, we establish necessary and sufficient conditions for identifying these quantities. Second, motivated by advances in label shift and PU learning, we propose practical methods for both tasks that leverage black-box predictors. Unlike typical Open Set Domain Adaptation (OSDA) problems, which tend to be ill-posed and amenable only to heuristics, OSLS offers a well-posed problem amenable to more principled machinery. Experiments across numerous semi-synthetic benchmarks on vision, language, and medical datasets demonstrate that our methods consistently outperform OSDA baselines, achieving 10--25% improvements in target domain accuracy. Finally, we analyze the proposed methods, establishing finite-sample convergence to the true label marginal and convergence to optimal classifier for linear models in a Gaussian setup. Code is available at https://github.com/acmi-lab/Open-Set-Label-Shift.