mlsanityData to 14 Oct 2026

Towards Semi-supervised Learning with Non-random Missing Labels

arXiv 2308.08872 ↗First posted 17 Aug 2023cs.LG cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Semi-supervised learning (SSL) tackles the label missing problem by enabling the effective usage of unlabeled data. While existing SSL methods focus on the traditional setting, a practical and challenging scenario called label Missing Not At Random (MNAR) is usually ignored. In MNAR, the labeled and unlabeled data fall into different class distributions resulting in biased label imputation, which deteriorates the performance of SSL models. In this work, class transition tracking based Pseudo-Rectifying Guidance (PRG) is devised for MNAR. We explore the class-level guidance information obtained by the Markov random walk, which is modeled on a dynamically created graph built over the class tracking matrix. PRG unifies the historical information of class distribution and class transitions caused by the pseudo-rectifying procedure to maintain the model's unbiased enthusiasm towards assigning pseudo-labels to all classes, so as the quality of pseudo-labels on both popular classes and rare classes in MNAR could be improved. Finally, we show the superior performance of PRG across a variety of MNAR scenarios, outperforming the latest SSL approaches combining bias removal solutions by a large margin. Code and model weights are available at https://github.com/NJUyued/PRG4SSL-MNAR.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 24 of its 41 references that are in the map. First posted on arXiv 17 Aug 2023.

Builds on

24 of 41 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Wide Residual Networkscited by 3,070
  3. 2016Matching Networks for One Shot Learningcited by 2,255
  4. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  5. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  6. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  7. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 605
  8. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 540
  9. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 510
  10. 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
  11. 2015Semi-Supervised Learning with Ladder Networkscited by 247
  12. 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 175
12 more
  1. 2020CoMatch: Semi-supervised Learning with Contrastive Graph Regularizationcited by 167
  2. 2021Dash: Semi-Supervised Learning with Dynamic Thresholdingcited by 148
  3. 2022SimMatch: Semi-supervised Learning with Similarity Matchingcited by 118
  4. 2020Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learningcited by 105
  5. 2020Context-aware Feature Generation for Zero-shot Semantic Segmentationcited by 94
  6. 2015Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labelscited by 64
  7. 2022Class-Aware Contrastive Semi-Supervised Learningcited by 62
  8. 2021Sinkhorn Label Allocation: Semi-Supervised Classification via Annealed Self-Trainingcited by 32
  9. 2020AlphaMatch: Improving Consistency for Semi-supervised Learning with Alpha-divergencecited by 22
  10. 2022MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularizationcited by 22
  11. 2022On Non-Random Missing Labels in Semi-Supervised Learningcited by 11
  12. 2022RDA: Reciprocal Distribution Alignment for Robust Semi-supervised Learningcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 5; 2025: 4; 2026: 1.

12 papers.

  1. 2024Constructing and Exploring Intermediate Domains in Mixed Domain Semi-supervised Medical Image Segmentationcited by 14
  2. 2024WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognitioncited by 10
  3. 2023PG-LBO: Enhancing High-Dimensional Bayesian Optimization with Pseudo-Label and Gaussian Process Guidancecited by 9
  4. 2023Roll With the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learningcited by 7
  5. 2025Causal Representation Learning from Multimodal Clinical Records under Non-Random Modality Missingnesscited by 5
  6. 2024PC2: Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrievalcited by 3
  7. 2025Divide-and-Conquer for Enhancing Unlabeled Learning, Stability, and Plasticity in Semi-supervised Continual Learningcited by 3
  8. 2024Rethinking Open-World Semi-Supervised Learning: Distribution Mismatch and Inductive Inferencecited by 0
  9. 2024Source-Free Test-Time Adaptation For Online Surface-Defect Detectioncited by 0
  10. 2025An Adaptor for Triggering Semi-Supervised Learning to Out-of-Box Serve Deep Image Clusteringcited by 0
  11. 2025The Good, the Bad, and the Sampled: a No-Regret Approach to Safe Online Classificationcited by 0
  12. 2026FastBUS: A Fast Bayesian Framework for Unified Weakly-Supervised Learningcited by 0