mlsanityData to 7 Oct 2026

Generative Adversarial Active Learning

arXiv 1702.07956 ↗First posted 25 Feb 2017cs.LG stat.MLcited by 69

Not on the map. Why?

Abstract (arXiv)

We propose a new active learning by query synthesis approach using Generative Adversarial Networks (GAN). Different from regular active learning, the resulting algorithm adaptively synthesizes training instances for querying to increase learning speed. We generate queries according to the uncertainty principle, but our idea can work with other active learning principles. We report results from various numerical experiments to demonstrate the effectiveness the proposed approach. In some settings, the proposed algorithm outperforms traditional pool-based approaches. To the best our knowledge, this is the first active learning work using GAN.

Key facts. Cited by 69 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Feb 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 19; 2023: 12; 2024: 12; 2025: 9; 2026: 5.

69 papers.

Sort:

By area:

  1. 2023Eliciting Human Preferences with Language Modelscited by 90
  2. 2022A Comparative Survey of Deep Active Learningcited by 88
  3. 2024A Survey on Deep Active Learning: Recent Advances and New Frontierscited by 53
  4. 2021Semi-Supervised Active Learning with Temporal Output Discrepancycited by 50
  5. 2023Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigmcited by 36
  6. 2023A comprehensive survey on deep active learning in medical image analysiscited by 32
  7. 2023Active learning for data streams: a surveycited by 29
  8. 2021Interpretability-Driven Sample Selection Using Self Supervised Learning For Disease Classification And Segmentationcited by 22
  9. 2022Open Long-Tailed Recognition in a Dynamic Worldcited by 21
  10. 2021Boosting Active Learning via Improving Test Performancecited by 19
  11. 2021MCDAL: Maximum Classifier Discrepancy for Active Learningcited by 18
  12. 2022Semantic Segmentation with Active Semi-Supervised Learningcited by 16
38 more
  1. 2022Deep Active Learning with Noise Stabilitycited by 13
  2. 2021Supervised Anomaly Detection via Conditional Generative Adversarial Network and Ensemble Active Learningcited by 11
  3. 2022Active Exploration for Neural Global Illumination of Variable Scenescited by 11
  4. 2022Human-Centric Artificial Intelligence Architecture for Industry 5.0 Applicationscited by 11
  5. 2022TiDAL: Learning Training Dynamics for Active Learningcited by 11
  6. 2023Accelerating Batch Active Learning Using Continual Learning Techniquescited by 8
  7. 2022Deep Active Learning for Computer Vision: Past and Futurecited by 7
  8. 2021When Deep Learners Change Their Mind: Learning Dynamics for Active Learningcited by 6
  9. 2021Towards General and Efficient Active Learningcited by 6
  10. 2025Rethinking Epistemic and Aleatoric Uncertainty for Active Open-Set Annotation: An Energy-Based Approachcited by 5
  11. 2024Generative Active Learning for Image Synthesis Personalizationcited by 4
  12. 2025Graph Neural Network and Transformer Integration for Unsupervised System Anomaly Discoverycited by 4
  13. 2021Active Learning Under Malicious Mislabeling and Poisoning Attackscited by 3
  14. 2021A critical look at the current train/test split in machine learningcited by 3
  15. 2022MUS-CDB: Mixed Uncertainty Sampling with Class Distribution Balancing for Active Annotation in Aerial Object Detectioncited by 3
  16. 2023REAL: A Representative Error-Driven Approach for Active Learningcited by 3
  17. 2024User-Side Realizationcited by 3
  18. 2021Active Learning to Classify Macromolecular Structures in situ for Less Supervision in Cryo-Electron Tomographycited by 2
  19. 2022Temporal Output Discrepancy for Loss Estimation-based Active Learningcited by 2
  20. 2025Unique Rashomon Sets for Robust Active Learningcited by 2
  21. 2021Data Efficient Human Intention Prediction: Leveraging Neural Network Verification and Expert Guidancecited by 1
  22. 2022Active Nearest Neighbor Regression Through Delaunay Refinementcited by 1
  23. 2022An Adversarial Active Sampling-based Data Augmentation Framework for Manufacturable Chip Designcited by 1
  24. 2022The Lean Data Scientist: Recent Advances towards Overcoming the Data Bottleneckcited by 1
  25. 2023Improving Classifier Robustness through Active Generation of Pairwise Counterfactualscited by 1
  26. 2023Learning Objective-Specific Active Learning Strategies with Attentive Neural Processescited by 1
  27. 2023Benchmarking of Query Strategies: Towards Future Deep Active Learningcited by 1
  28. 2023Reinforcement-based Display-size Selection for Frugal Satellite Image Change Detectioncited by 1
  29. 2024Generative Subspace Adversarial Active Learning for Outlier Detection in Multiple Views of High-dimensional Datacited by 1
  30. 2024Robust Active Learning (RoAL): Countering Dynamic Adversaries in Active Learning with Elastic Weight Consolidationcited by 1
  31. 2024MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active Learningcited by 1
  32. 2024AutoAL: Automated Active Learning with Differentiable Query Strategy Searchcited by 1
  33. 2024GALOT: Generative Active Learning via Optimizable Zero-shot Text-to-image Generationcited by 1
  34. 2025OFAL: An Oracle-Free Active Learning Frameworkcited by 1
  35. 2026ACIL: Active Class Incremental Learning for Image Classificationcited by 1
  36. 2026Portable Active Learning for Object Detectioncited by 1
  37. 2021Knowledge Modelling and Active Learning in Manufacturingcited by 0
  38. 2022Towards Robust Deep Active Learning for Scientific Computingcited by 0

50 most cited of 69 All 69 (JSON)