mlsanityData to 7 Oct 2026

How to Select Which Active Learning Strategy is Best Suited for Your Specific Problem and Budget

arXiv 2306.03543 ↗First posted 6 Jun 2023cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

In the domain of Active Learning (AL), a learner actively selects which unlabeled examples to seek labels from an oracle, while operating within predefined budget constraints. Importantly, it has been recently shown that distinct query strategies are better suited for different conditions and budgetary constraints. In practice, the determination of the most appropriate AL strategy for a given situation remains an open problem. To tackle this challenge, we propose a practical derivative-based method that dynamically identifies the best strategy for a given budget. Intuitive motivation for our approach is provided by the theoretical analysis of a simplified scenario. We then introduce a method to dynamically select an AL strategy, which takes into account the unique characteristics of the problem and the available budget. Empirical results showcase the effectiveness of our approach across diverse budgets and computer vision tasks.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 26 of its 42 references that are in the map. First posted on arXiv 6 Jun 2023.

Builds on

26 of 42 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  4. 2017Deep Bayesian Active Learning with Image Datacited by 812
  5. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  6. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  7. 2020SCAN: Learning to Classify Images without Labelscited by 351
  8. 2019On The Power of Curriculum Learning in Training Deep Networkscited by 285
  9. 2019Variational Adversarial Active Learningcited by 284
  10. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 131
  11. 2019Discriminative Active Learningcited by 97
  12. 2019Deep Active Learning: Unified and Principled Method for Query and Trainingcited by 92
14 more
  1. 2022Active Learning Through a Covering Lenscited by 62
  2. 2019Let's Agree to Agree: Neural Networks Share Classification Order on Real Datasetscited by 55
  3. 2020Towards Robust and Reproducible Active Learning Using Neural Networkscited by 53
  4. 2020A Survey of Active Learning for Text Classification using Deep Neural Networkscited by 50
  5. 2019Parting with Illusions about Deep Active Learningcited by 38
  6. 2021The Grammar-Learning Trajectories of Neural Language Modelscited by 36
  7. 2021Low Budget Active Learning via Wasserstein Distance: An Integer Programming Approachcited by 34
  8. 2022Making Your First Choice: To Address Cold Start Problem in Vision Active Learningcited by 25
  9. 2020On the Marginal Benefit of Active Learning: Does Self-Supervision Eat Its Cake?cited by 18
  10. 2023Algorithm Selection for Deep Active Learning with Imbalanced Datasetscited by 18
  11. 2022Optimizing Data Collection for Machine Learningcited by 15
  12. 2021Principal Components Bias in Over-parameterized Linear Models, and its Manifestation in Deep Neural Networkscited by 10
  13. 2018Dynamic Ensemble Active Learning: A Non-Stationary Bandit with Expert Advicecited by 6
  14. 2023A Meta-Learning Approach to Predicting Performance and Data Requirementscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 4; 2026: 4.

16 papers.

Sort:

By area:

  1. 2024Generalized Coverage for More Robust Low-Budget Active Learningcited by 15
  2. 2024Uncertainty Herding: One Active Learning Method for All Label Budgetscited by 12
  3. 2024Predicting the Susceptibility of Examples to Catastrophic Forgettingcited by 7
  4. 2024Bridging Diversity and Uncertainty in Active learning with Self-Supervised Pre-Trainingcited by 6
  5. 2024Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classificationcited by 6
  6. 2025Enhancing Cost Efficiency in Active Learning with Candidate Set Querycited by 3
  7. 2025Active Learning with a Noisy Annotatorcited by 3
  8. 2024DCoM: Active Learning for All Learnerscited by 2
  9. 2024Active Prompt Learning with Vision-Language Model Priorscited by 2
  10. 2025Cleaning the Pool: Progressive Filtering of Unlabeled Pools in Deep Active Learningcited by 2
  11. 2024AutoAL: Automated Active Learning with Differentiable Query Strategy Searchcited by 1
  12. 2026BoSS: A Best-of-Strategies Selector as an Oracle for Deep Active Learningcited by 1
4 more
  1. 2025PCoreSet: Effective Active Learning through Knowledge Distillation from Vision-Language Modelscited by 0
  2. 2026Federated Active Learning Under Extreme Non-IID and Global Class Imbalancecited by 0
  3. 2026Dataset-Aware Cold-Start Active Learning for Annotation-Efficient 3D Medical Image Segmentationcited by 0
  4. 2026Train Smarter, Not Harder: Switching Signal-Guided Training in Active Learningcited by 0