mlsanityData to 7 Oct 2026

A Theory of Label Propagation for Subpopulation Shift

arXiv 2102.11203 ↗First posted 22 Feb 2021cs.LG cs.AI stat.MLcited by 48

Not on the map. Why?

Abstract (arXiv)

One of the central problems in machine learning is domain adaptation. Unlike past theoretical work, we consider a new model for subpopulation shift in the input or representation space. In this work, we propose a provably effective framework for domain adaptation based on label propagation. In our analysis, we use a simple but realistic expansion assumption, proposed in citetwei2021theoretical. Using a teacher classifier trained on the source domain, our algorithm not only propagates to the target domain but also improves upon the teacher. By leveraging existing generalization bounds, we also obtain end-to-end finite-sample guarantees on the entire algorithm. In addition, we extend our theoretical framework to a more general setting of source-to-target transfer based on a third unlabeled dataset, which can be easily applied in various learning scenarios. Inspired by our theory, we adapt consistency-based semi-supervised learning methods to domain adaptation settings and gain significant improvements.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Builds on 49 of its 85 references that are in the map. First posted on arXiv 22 Feb 2021.

Builds on

49 of 85 references.

References · 49

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  4. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  5. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  6. 2019Invariant Risk Minimizationcited by 1,832
  7. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  8. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  9. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  10. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  11. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
  12. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
37 more
  1. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  2. 2020In Search of Lost Domain Generalizationcited by 1,042
  3. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  4. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  5. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  6. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
  7. 2019Bridging Theory and Algorithm for Domain Adaptationcited by 332
  8. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  9. 2019Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptationcited by 235
  10. 2020How Neural Networks Extrapolate: From Feedforward to Graph Neural Networkscited by 218
  11. 2018A DIRT-T Approach to Unsupervised Domain Adaptationcited by 215
  12. 2020Representation Learning via Invariant Causal Mechanismscited by 197
  13. 2018Multi-Adversarial Domain Adaptationcited by 195
  14. 2020Invariant Risk Minimization Gamescited by 188
  15. 2020Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Datacited by 179
  16. 2020BREEDS: Benchmarks for Subpopulation Shiftcited by 155
  17. 2020Understanding Self-Training for Gradual Domain Adaptationcited by 149
  18. 2018Deep Co-Training for Semi-Supervised Image Recognitioncited by 145
  19. 2020Learning explanations that are hard to varycited by 132
  20. 2019Multi-adversarial Faster-RCNN for Unrestricted Object Detectioncited by 111
  21. 2018Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shiftcited by 109
  22. 2020A Review of Single-Source Deep Unsupervised Visual Domain Adaptationcited by 96
  23. 2019HoMM: Higher-order Moment Matching for Unsupervised Domain Adaptationcited by 89
  24. 2014Domain-Adversarial Neural Networkscited by 78
  25. 2019Multi-source Domain Adaptation for Semantic Segmentationcited by 74
  26. 2020Self-training Avoids Using Spurious Features Under Domain Shiftcited by 69
  27. 2019Unsupervised Domain Adaptation using Feature-Whitening and Consensus Losscited by 67
  28. 2019Domain Adaptation with Asymmetrically-Relaxed Distribution Alignmentcited by 61
  29. 2019Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margincited by 56
  30. 2019On Learning Invariant Representation for Domain Adaptationcited by 38
  31. 2020Fundamental Limits and Tradeoffs in Invariant Representation Learningcited by 38
  32. 2020Rethinking Distributional Matching Based Domain Adaptationcited by 33
  33. 2019Multi-level Domain Adaptive learning for Cross-Domain Detectioncited by 30
  34. 2016Generative Adversarial Nets from a Density Ratio Estimation Perspectivecited by 24
  35. 2020Learning Causal Models Onlinecited by 18
  36. 2014Adaptation Algorithm and Theory Based on Generalized Discrepancycited by 9
  37. 2019Butterfly: One-step Approach towards Wildly Unsupervised Domain Adaptationcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 15; 2023: 11; 2024: 5; 2025: 6; 2026: 3.

48 papers.

Sort:

By area:

  1. 2022Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distributioncited by 722
  2. 2021Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Losscited by 311
  3. 2021Cycle Self-Training for Domain Adaptationcited by 120
  4. 2021Towards a Theoretical Framework of Out-of-Distribution Generalizationcited by 94
  5. 2022Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptationcited by 66
  6. 2022Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learningcited by 53
  7. 2024Theoretical Analysis of Weak-to-Strong Generalizationcited by 46
  8. 2022Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulationscited by 44
  9. 2021Near-Optimal Linear Regression under Distribution Shiftcited by 40
  10. 2022Invariant and Transportable Representations for Anti-Causal Domain Shiftscited by 37
  11. 2021If your data distribution shifts, use self-learningcited by 36
  12. 2022Sample Efficiency of Data Augmentation Consistency Regularizationcited by 28
36 more
  1. 2022Transferring Fairness under Distribution Shifts via Fair Consistency Regularizationcited by 21
  2. 2022First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domainscited by 20
  3. 2021Self-training Converts Weak Learners to Strong Learners in Mixture Modelscited by 19
  4. 2022Localized Adversarial Domain Generalizationcited by 19
  5. 2023Pseudo-Labeling for Kernel Ridge Regression under Covariate Shiftcited by 17
  6. 2023GeoNet: Benchmarking Unsupervised Adaptation across Geographiescited by 17
  7. 2022Understanding new tasks through the lens of training data via exponential tiltingcited by 11
  8. 2024The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignmentcited by 11
  9. 2024Controllable Prompt Tuning For Balancing Group Distributional Robustnesscited by 10
  10. 2025Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimensioncited by 10
  11. 2022Label Propagation with Weak Supervisioncited by 9
  12. 2022Can domain adaptation make object recognition work for everyone?cited by 8
  13. 2023Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clusteringcited by 7
  14. 2025Mitigating Spurious Correlation via Distributionally Robust Learning with Hierarchical Ambiguity Setscited by 7
  15. 2023Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shiftcited by 5
  16. 2023DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learningcited by 4
  17. 2023Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shiftcited by 4
  18. 2021Encoding Hierarchical Information in Neural Networks helps in Subpopulation Shiftcited by 3
  19. 2024Optimizing importance weighting in the presence of sub-population shiftscited by 3
  20. 2025Analyzing Similarity Metrics for Data Selection for Language Model Pretrainingcited by 3
  21. 2025Mitigating Confounding in Speech-Based Dementia Detection through Weight Maskingcited by 3
  22. 2023Pushing the Accuracy-Group Robustness Frontier with Introspective Self-playcited by 2
  23. 2023On the Stability and Generalization of Triplet Learningcited by 2
  24. 2023Controlling Federated Learning for Covertnesscited by 2
  25. 2024Bridging Domains with Approximately Shared Featurescited by 2
  26. 2022GOCA: Guided Online Cluster Assignment for Self-Supervised Video Representation Learningcited by 1
  27. 2023IW-GAE: Importance Weighted Group Accuracy Estimation for Improved Calibration and Model Selection in Unsupervised Domain Adaptationcited by 1
  28. 2021Can semi-supervised learning reduce the amount of manual labelling required for effective radio galaxy morphology classification?cited by 0
  29. 2022Dual-Correction Adaptation Network for Noisy Knowledge Transfercited by 0
  30. 2022Cross-client Label Propagation for Transductive and Semi-Supervised Federated Learningcited by 0
  31. 2023Chaos to Order: A Label Propagation Perspective on Source-Free Domain Adaptationcited by 0
  32. 2025References Indeed Matter? Reference-Free Preference Optimization for Conversational Query Reformulationcited by 0
  33. 2025Exploiting Vision Language Model for Training-Free 3D Point Cloud OOD Detection via Graph Score Propagationcited by 0
  34. 2026Learning from Limited Labels: Transductive Graph Label Propagation for Indian Music Analysiscited by 0
  35. 2026Black-Box Assisted Regression: Phase Transitions and Minimax Optimalitycited by 0
  36. 2026Learning the Robustness Mechanism with Bilevel Optimizationcited by 0