mlsanityData to 14 Oct 2026

Domain Adaptation under Open Set Label Shift

arXiv 2207.13048 ↗First posted 26 Jul 2022cs.LGcited by 32

Not on the map. Why?

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.

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

48 of 96 references.

References · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  6. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  7. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  8. 2016Understanding deep learning requires rethinking generalizationcited by 1,674
  9. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  10. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  11. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  12. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
36 more
  1. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  2. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  3. 2017Selective Classification for Deep Neural Networkscited by 852
  4. 2017The Implicit Bias of Gradient Descent on Separable Datacited by 655
  5. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 612
  6. 2019Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networkscited by 566
  7. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 416
  8. 2018Detecting and Correcting for Label Shift with Black Box Predictorscited by 366
  9. 2019Bridging Theory and Algorithm for Domain Adaptationcited by 332
  10. 2014Towards Open World Recognitioncited by 226
  11. 2017Positive-Unlabeled Learning with Non-Negative Risk Estimatorcited by 219
  12. 2018Learning from positive and unlabeled data: a surveycited by 219
  13. 2018To Trust Or Not To Trust A Classifiercited by 207
  14. 2020Universal Domain Adaptation through Self Supervisioncited by 172
  15. 2021Open-World Semi-Supervised Learningcited by 165
  16. 2020BREEDS: Benchmarks for Subpopulation Shiftcited by 155
  17. 2018Open Set Domain Adaptation by Backpropagationcited by 150
  18. 2016Correlation Alignment for Unsupervised Domain Adaptationcited by 147
  19. 2022Leveraging Unlabeled Data to Predict Out-of-Distribution Performancecited by 145
  20. 2019Regularized Learning for Domain Adaptation under Label Shiftscited by 120
  21. 2020A Unified View of Label Shift Estimationcited by 119
  22. 2020Hybrid Models for Open Set Recognitioncited by 109
  23. 2019Learning to Transfer Examples for Partial Domain Adaptationcited by 87
  24. 2021Extending the WILDS Benchmark for Unsupervised Adaptationcited by 86
  25. 2020On the Effectiveness of Image Rotation for Open Set Domain Adaptationcited by 72
  26. 2020Coping with Label Shift via Distributionally Robust Optimisationcited by 70
  27. 2016Mixture Proportion Estimation via Kernel Embedding of Distributionscited by 67
  28. 2021Mixture Proportion Estimation and PU Learning: A Modern Approachcited by 52
  29. 2020Self-PU: Self Boosted and Calibrated Positive-Unlabeled Trainingcited by 47
  30. 2021RATT: Leveraging Unlabeled Data to Guarantee Generalizationcited by 20
  31. 2018Breast Cancer Classification from Histopathological Images with Inception Recurrent Residual Convolutional Neural Networkcited by 15
  32. 2016Nonparametric semi-supervised learning of class proportionscited by 13
  33. 2018Learning Factorized Representations for Open-set Domain Adaptationcited by 13
  34. 2019Weakly Supervised Open-set Domain Adaptation by Dual-domain Collaborationcited by 8
  35. 2013Class Proportion Estimation with Application to Multiclass Anomaly Rejectioncited by 6
  36. 2019Known-class Aware Self-ensemble for Open Set Domain Adaptationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 11; 2024: 6; 2025: 12; 2026: 1.

32 papers.

Sort:

By area:

  1. 2023Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detectioncited by 57
  2. 2024How Does Unlabeled Data Provably Help Out-of-Distribution Detection?cited by 36
  3. 2023RLSbench: Domain Adaptation Under Relaxed Label Shiftcited by 30
  4. 2023PAC Prediction Sets Under Label Shiftcited by 21
  5. 2024A Short Survey on Importance Weighting for Machine Learningcited by 15
  6. 2025Handling Out-of-Distribution Data: A Surveycited by 14
  7. 2022A Closer Look at Novel Class Discovery from the Labeled Setcited by 12
  8. 2023Online Label Shift: Optimal Dynamic Regret meets Practical Algorithmscited by 11
  9. 2023Imbalanced Open Set Domain Adaptation via Moving-threshold Estimation and Gradual Alignmentcited by 9
  10. 2023ELSA: Efficient Label Shift Adaptation through the Lens of Semiparametric Modelscited by 9
  11. 2023Generalized Universal Domain Adaptation with Generative Flow Networkscited by 7
  12. 2024Cross-domain Open-world Discoverycited by 6
20 more
  1. 2023Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shiftcited by 5
  2. 2025Out-of-Distribution Detection using Synthetic Data Generationcited by 4
  3. 2024Positive and Unlabeled Data: Model, Estimation, Inference, and Classificationcited by 3
  4. 2023Federated Learning with Uncertainty-Based Client Clustering for Fleet-Wide Fault Diagnosiscited by 2
  5. 2025Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergiescited by 2
  6. 2025OASIS: Open-world Adaptive Self-supervised and Imbalanced-aware Systemcited by 2
  7. 2025Medix: Out-of-Distribution Detection from Unlabeled Wild Data via Robust Gradient Statisticscited by 2
  8. 2022Contrastive Novelty-Augmented Learning: Anticipating Outliers with Large Language Modelscited by 1
  9. 2023Generalized Out-of-distribution Fault Diagnosis (GOOFD) via Internal Contrastive Learningcited by 1
  10. 2024Novel Node Category Detection Under Subpopulation Shiftcited by 1
  11. 2024On the KL-Divergence-based Robust Satisficing Modelcited by 1
  12. 2025Addressing Label Shift in Distributed Learning via Entropy Regularizationcited by 1
  13. 2025Open Set Label Shift with Test Time Out-of-Distribution Referencecited by 1
  14. 2023Heterogeneous Domain Adaptation with Positive and Unlabeled Datacited by 0
  15. 2025Semiparametric Learning from Open-Set Label Shift Datacited by 0
  16. 2025Unsupervised Domain Adaptation for Binary Classification with an Unobservable Source Subpopulationcited by 0
  17. 2025Information Theory in Open-world Machine Learning Foundations, Frameworks, and Future Directioncited by 0
  18. 2025Unlocking Out-of-Distribution Generalization in Dynamics through Physics-Guided Augmentationcited by 0
  19. 2025Open-Set Domain Adaptation Under Background Distribution Shift: Challenges and A Provably Efficient Solutioncited by 0
  20. 2026Mixture Proportion Estimation and Weakly-supervised Kernel Test for Conditional Independencecited by 0