mlsanityData to 7 Oct 2026

Learning how to Active Learn: A Deep Reinforcement Learning Approach

arXiv 1708.02383 ↗First posted 8 Aug 2017cs.CL cs.AI cs.LGcited by 79

Not on the map. Why?

Abstract (arXiv)

Active learning aims to select a small subset of data for annotation such that a classifier learned on the data is highly accurate. This is usually done using heuristic selection methods, however the effectiveness of such methods is limited and moreover, the performance of heuristics varies between datasets. To address these shortcomings, we introduce a novel formulation by reframing the active learning as a reinforcement learning problem and explicitly learning a data selection policy, where the policy takes the role of the active learning heuristic. Importantly, our method allows the selection policy learned using simulation on one language to be transferred to other languages. We demonstrate our method using cross-lingual named entity recognition, observing uniform improvements over traditional active learning.

Key facts. Cited by 79 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 18; 2023: 11; 2024: 13; 2025: 8; 2026: 8.

79 papers.

Sort:

By area:

  1. 2022Active Example Selection for In-Context Learningcited by 195
  2. 2021Active Learning by Acquiring Contrastive Examplescited by 154
  3. 2021Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forwardcited by 82
  4. 2024A Survey on Deep Active Learning: Recent Advances and New Frontierscited by 53
  5. 2021Diminishing Uncertainty within the Training Pool: Active Learning for Medical Image Segmentationcited by 44
  6. 2022A Survey of Active Learning for Natural Language Processingcited by 40
  7. 2021Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimatescited by 39
  8. 2023Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigmcited by 36
  9. 2023Active learning for data streams: a surveycited by 29
  10. 2021Learning with Different Amounts of Annotation: From Zero to Many Labelscited by 28
  11. 2021Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Trainingcited by 19
  12. 2024The Why, When, and How to Use Active Learning in Large-Data-Driven 3D Object Detection for Safe Autonomous Driving: An Empirical Explorationcited by 17
38 more
  1. 2022Dynamic Contrastive Distillation for Image-Text Retrievalcited by 14
  2. 2021A Framework for Learning to Request Rich and Contextually Useful Information from Humanscited by 12
  3. 2021Generalization in Text-based Games via Hierarchical Reinforcement Learningcited by 11
  4. 2022Towards Computationally Feasible Deep Active Learningcited by 11
  5. 2022Perceiving the World: Question-guided Reinforcement Learning for Text-based Gamescited by 10
  6. 2022Asking for Knowledge: Training RL Agents to Query External Knowledge Using Languagecited by 10
  7. 2021Multiple-criteria Based Active Learning with Fixed-size Determinantal Point Processescited by 9
  8. 2024Corpus Considerations for Annotator Modeling and Scalingcited by 8
  9. 2023On the Opportunities of Green Computing: A Surveycited by 7
  10. 2021Capturing Label Distribution: A Case Study in NLIcited by 6
  11. 2021Multi-Domain Active Learning: Literature Review and Comparative Studycited by 6
  12. 2021Towards General and Efficient Active Learningcited by 6
  13. 2022Active learning using adaptable task-based prioritisationcited by 6
  14. 2022Onception: Active Learning with Expert Advice for Real World Machine Translationcited by 5
  15. 2022A Survey of Dataset Refinement for Problems in Computer Vision Datasetscited by 5
  16. 2022Combining Data Generation and Active Learning for Low-Resource Question Answeringcited by 5
  17. 2025Active Advantage-Aligned Online Reinforcement Learning with Offline Datacited by 5
  18. 2025Rethinking Epistemic and Aleatoric Uncertainty for Active Open-Set Annotation: An Energy-Based Approachcited by 5
  19. 2021A Survey on Active Deep Learning: From Model-driven to Data-drivencited by 4
  20. 2021ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detectioncited by 4
  21. 2022FINETUNA: Fine-tuning Accelerated Molecular Simulationscited by 4
  22. 2022When Bioprocess Engineering Meets Machine Learning: A Survey from the Perspective of Automated Bioprocess Developmentcited by 4
  23. 2025MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretrainingcited by 4
  24. 2021ImitAL: Learning Active Learning Strategies from Synthetic Datacited by 3
  25. 2022Budget-aware Few-shot Learning via Graph Convolutional Networkcited by 3
  26. 2022Challenges and Opportunities for Machine Learning Classification of Behavior and Mental State from Imagescited by 3
  27. 2022Deep reinforced active learning for multi-class image classificationcited by 3
  28. 2023Active Continual Learning: On Balancing Knowledge Retention and Learnabilitycited by 3
  29. 2023A Minimal Approach for Natural Language Action Space in Text-based Gamescited by 3
  30. 2023REAL: A Representative Error-Driven Approach for Active Learningcited by 3
  31. 2023Learning to Rank for Active Learning via Multi-Task Bilevel Optimizationcited by 3
  32. 2021Adaptive Selection of Informative Path Planning Strategies via Reinforcement Learningcited by 2
  33. 2024Amortized nonmyopic active search via deep imitation learningcited by 2
  34. 2024Augmenting Biomedical Named Entity Recognition with General-domain Resourcescited by 2
  35. 2021Reinforcement Learning Approach to Active Learning for Image Classificationcited by 1
  36. 2022ImitAL: Learned Active Learning Strategy on Synthetic Datacited by 1
  37. 2023Progressively Efficient Learningcited by 1
  38. 2023Exploring Active Learning in Meta-Learning: Enhancing Context Set Labelingcited by 1

50 most cited of 79 All 79 (JSON)