mlsanityData to 7 Oct 2026

Algorithm Selection for Deep Active Learning with Imbalanced Datasets

arXiv 2302.07317 ↗First posted 14 Feb 2023cs.LG cs.AI cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

Label efficiency has become an increasingly important objective in deep learning applications. Active learning aims to reduce the number of labeled examples needed to train deep networks, but the empirical performance of active learning algorithms can vary dramatically across datasets and applications. It is difficult to know in advance which active learning strategy will perform well or best in a given application. To address this, we propose the first adaptive algorithm selection strategy for deep active learning. For any unlabeled dataset, our (meta) algorithm TAILOR (Thompson ActIve Learning algORithm selection) iteratively and adaptively chooses among a set of candidate active learning algorithms. TAILOR uses novel reward functions aimed at gathering class-balanced examples. Extensive experiments in multi-class and multi-label applications demonstrate TAILOR's effectiveness in achieving accuracy comparable or better than that of the best of the candidate algorithms. Our implementation of TAILOR is open-sourced at https://github.com/jifanz/TAILOR.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 27 of its 61 references that are in the map. First posted on arXiv 14 Feb 2023.

Builds on

27 of 61 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2017Deep Bayesian Active Learning with Image Datacited by 812
  5. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  6. 2018Deep Learning for Classical Japanese Literaturecited by 415
  7. 2013Learning to Optimize Via Posterior Samplingcited by 253
  8. 2018Adversarial Active Learning for Deep Networks: a Margin Based Approachcited by 155
  9. 2021Batch Active Learning at Scalecited by 127
  10. 2017Learning Active Learning from Datacited by 100
  11. 2019Discriminative Active Learningcited by 97
  12. 2021Gone Fishing: Neural Active Learning with Fisher Embeddingscited by 88
15 more
  1. 2022A Comparative Survey of Deep Active Learningcited by 88
  2. 2021SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarioscited by 83
  3. 2017Deep Active Learning over the Long Tailcited by 82
  4. 2021Effective Evaluation of Deep Active Learning on Image Classification Taskscited by 37
  5. 2021Deep Active Learning by Leveraging Training Dynamicscited by 32
  6. 2022GALAXY: Graph-based Active Learning at the Extremecited by 29
  7. 2021Active Learning at the ImageNet Scalecited by 28
  8. 2022Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernelscited by 25
  9. 2020Similarity Search for Efficient Active Learning and Search of Rare Conceptscited by 24
  10. 2022A Lagrangian Duality Approach to Active Learningcited by 24
  11. 2019Learning to Sample: an Active Learning Frameworkcited by 11
  12. 2018Dynamic Ensemble Active Learning: A Non-Stationary Bandit with Expert Advicecited by 6
  13. 2020IALE: Imitating Active Learner Ensemblescited by 3
  14. 2021ImitAL: Learning Active Learning Strategies from Synthetic Datacited by 3
  15. 2020Learning to Actively Learn: A Robust Approachcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 8; 2025: 4; 2026: 4.

18 papers.

Sort:

By area:

  1. 2023How to Select Which Active Learning Strategy is Best Suited for Your Specific Problem and Budgetcited by 16
  2. 2023Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separationcited by 8
  3. 2024Out-of-Distribution Learning with Human Feedbackcited by 6
  4. 2024Deep Active Learning in the Open Worldcited by 5
  5. 2024Learning from the Best: Active Learning for Wireless Communicationscited by 4
  6. 2024AnchorAL: Computationally Efficient Active Learning for Large and Imbalanced Datasetscited by 4
  7. 2025Cohort-Based Active Modality Acquisitioncited by 4
  8. 2024Active Learning with Context Sampling and One-vs-Rest Entropy for Semantic Segmentationcited by 2
  9. 2024COBRA: COmBinatorial Retrieval Augmentation for Few-Shot Adaptationcited by 2
  10. 2025Cleaning the Pool: Progressive Filtering of Unlabeled Pools in Deep Active Learningcited by 2
  11. 2024Class-Balanced and Reinforced Active Learning on Graphscited by 1
  12. 2024AutoAL: Automated Active Learning with Differentiable Query Strategy Searchcited by 1
6 more
  1. 2026Labeled TrustSet Guided: Batch Active Learning with Reinforcement Learningcited by 1
  2. 2025TS-Insight: Visualizing Thompson Sampling for Verification and XAIcited by 0
  3. 2025Active Learning with Task-Driven Representations for Messy Poolscited by 0
  4. 2026CAAL: Contextual Bandits based Online Hand-Craft Active Learning Strategy Selectioncited by 0
  5. 2026ALIVE: Warnings Before Exclusion in Budgeted Multi-Source Learningcited by 0
  6. 2026Train Smarter, Not Harder: Switching Signal-Guided Training in Active Learningcited by 0