mlsanityData to 7 Oct 2026

Robust Semi-Supervised Learning in Open Environments

arXiv 2412.18256 ↗First posted 24 Dec 2024cs.LG cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Semi-supervised learning (SSL) aims to improve performance by exploiting unlabeled data when labels are scarce. Conventional SSL studies typically assume close environments where important factors (e.g., label, feature, distribution) between labeled and unlabeled data are consistent. However, more practical tasks involve open environments where important factors between labeled and unlabeled data are inconsistent. It has been reported that exploiting inconsistent unlabeled data causes severe performance degradation, even worse than the simple supervised learning baseline. Manually verifying the quality of unlabeled data is not desirable, therefore, it is important to study robust SSL with inconsistent unlabeled data in open environments. This paper briefly introduces some advances in this line of research, focusing on techniques concerning label, feature, and data distribution inconsistency in SSL, and presents the evaluation benchmarks. Open research problems are also discussed for reference purposes.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 31 of its 60 references that are in the map. First posted on arXiv 24 Dec 2024.

Builds on

31 of 60 references.

References · 31

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  3. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  4. 2022Large Language Models Can Self-Improvecited by 656
  5. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
  6. 2020Class-incremental learning: survey and performance evaluation on image classificationcited by 446
  7. 2018Recent Advances in Open Set Recognition: A Surveycited by 309
  8. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  9. 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 174
  10. 2021Open-World Semi-Supervised Learningcited by 165
  11. 2020Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learningcited by 105
  12. 2022USB: A Unified Semi-supervised Learning Benchmark for Classificationcited by 95
19 more
  1. 2020Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learningcited by 82
  2. 2021Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimizationcited by 66
  3. 2022How to Leverage Unlabeled Data in Offline Reinforcement Learningcited by 61
  4. 2019Robustness to Adversarial Perturbations in Learning from Incomplete Datacited by 49
  5. 2022Open-environment Machine Learningcited by 48
  6. 2021Poisoning the Unlabeled Dataset of Semi-Supervised Learningcited by 44
  7. 2021OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outlierscited by 43
  8. 2021Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learningcited by 40
  9. 2024LawGPT: A Chinese Legal Knowledge-Enhanced Large Language Modelcited by 34
  10. 2019A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learningcited by 30
  11. 2023S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captionscited by 29
  12. 2022Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectoriescited by 27
  13. 2024DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detectioncited by 14
  14. 2018Tangent-Normal Adversarial Regularization for Semi-supervised Learningcited by 10
  15. 2022Transfer and Share: Semi-Supervised Learning from Long-Tailed Datacited by 9
  16. 2018Distributionally Robust Semi-Supervised Learning for People-Centric Sensingcited by 8
  17. 2024Offline Imitation Learning with Model-based Reverse Augmentationcited by 8
  18. 2022LAMDA-SSL: Semi-Supervised Learning in Pythoncited by 5
  19. 2023DualMatch: Robust Semi-Supervised Learning with Dual-Level Interactioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 7; 2026: 1.

8 papers.

  1. 2025Vision-Language Model Selection and Reuse for Downstream Adaptationcited by 3
  2. 2025Re-Evaluating the Impact of Unseen-Class Unlabeled Data on Semi-Supervised Learning Modelcited by 3
  3. 2026Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Usecited by 3
  4. 2025BMIP: Bi-directional Modality Interaction Prompt Learning for VLMcited by 2
  5. 2025Applications and Effect Evaluation of Generative Adversarial Networks in Semi-Supervised Learningcited by 2
  6. 2025Weakly-Supervised Contrastive Learning for Imprecise Class Labelscited by 1
  7. 2025Probabilistic Hyper-Graphs using Multiple Randomly Masked Autoencoders for Semi-supervised Multi-modal Multi-task Learningcited by 1
  8. 2025Bi-CoG: Bi-Consistency-Guided Self-Training for Vision-Language Modelscited by 0