mlsanityData to 7 Oct 2026

GALAXY: Graph-based Active Learning at the Extreme

arXiv 2202.01402 ↗First posted 3 Feb 2022cs.LG cs.AI cs.CVcited by 29

Not on the map. Why?

Abstract (arXiv)

Active learning is a label-efficient approach to train highly effective models while interactively selecting only small subsets of unlabelled data for labelling and training. In "open world" settings, the classes of interest can make up a small fraction of the overall dataset -- most of the data may be viewed as an out-of-distribution or irrelevant class. This leads to extreme class-imbalance, and our theory and methods focus on this core issue. We propose a new strategy for active learning called GALAXY (Graph-based Active Learning At the eXtrEme), which blends ideas from graph-based active learning and deep learning. GALAXY automatically and adaptively selects more class-balanced examples for labeling than most other methods for active learning. Our theory shows that GALAXY performs a refined form of uncertainty sampling that gathers a much more class-balanced dataset than vanilla uncertainty sampling. Experimentally, we demonstrate GALAXY's superiority over existing state-of-art deep active learning algorithms in unbalanced vision classification settings generated from popular datasets.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 16 of its 32 references that are in the map. First posted on arXiv 3 Feb 2022.

Builds on

16 of 32 references.

References · 16

  1. 2017Deep Bayesian Active Learning with Image Datacited by 812
  2. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 682
  3. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  4. 2018Adversarial Active Learning for Deep Networks: a Margin Based Approachcited by 155
  5. 2021Batch Active Learning at Scalecited by 127
  6. 2020FairBatch: Batch Selection for Model Fairnesscited by 99
  7. 2019Discriminative Active Learningcited by 97
  8. 2021Gone Fishing: Neural Active Learning with Fisher Embeddingscited by 88
  9. 2021SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarioscited by 83
  10. 2017Deep Active Learning over the Long Tailcited by 82
  11. 2021Active Learning at the ImageNet Scalecited by 28
  12. 2020Similarity Search for Efficient Active Learning and Search of Rare Conceptscited by 24
4 more
  1. 2015S2: An Efficient Graph Based Active Learning Algorithm with Application to Nonparametric Classificationcited by 20
  2. 2021Improved Algorithms for Agnostic Pool-based Active Classificationcited by 15
  3. 2013Active Learning on Trees and Graphscited by 10
  4. 2020Diffusion-based Deep Active Learningcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 12; 2025: 4; 2026: 8.

29 papers.

Sort:

By area:

  1. 2024A Survey on Deep Active Learning: Recent Advances and New Frontierscited by 53
  2. 2024An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Modelscited by 22
  3. 2023LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learningcited by 20
  4. 2023Algorithm Selection for Deep Active Learning with Imbalanced Datasetscited by 18
  5. 2024Uncertainty for Active Learning on Graphscited by 11
  6. 2024A Cross-Domain Benchmark for Active Learningcited by 11
  7. 2023Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separationcited by 8
  8. 2024AHA: Human-Assisted Out-of-Distribution Generalization and Detectioncited by 7
  9. 2024Out-of-Distribution Learning with Human Feedbackcited by 6
  10. 2024Deep Active Learning in the Open Worldcited by 5
  11. 2024Learning from the Best: Active Learning for Wireless Communicationscited by 4
  12. 2024AnchorAL: Computationally Efficient Active Learning for Large and Imbalanced Datasetscited by 4
17 more
  1. 2023How To Overcome Confirmation Bias in Semi-Supervised Image Classification By Active Learningcited by 2
  2. 2024COBRA: COmBinatorial Retrieval Augmentation for Few-Shot Adaptationcited by 2
  3. 2022Active Few-Shot Classification: a New Paradigm for Data-Scarce Learning Settingscited by 1
  4. 2024Class-Balanced and Reinforced Active Learning on Graphscited by 1
  5. 2025Improving Task Diversity in Label Efficient Supervised Finetuning of LLMscited by 1
  6. 2026Labeled TrustSet Guided: Batch Active Learning with Reinforcement Learningcited by 1
  7. 2024EPS: Efficient Patch Sampling for Video Overfitting in Deep Super-Resolution Model Trainingcited by 0
  8. 2025Active Learning Methods for Efficient Data Utilization and Model Performance Enhancementcited by 0
  9. 2025Batch Bayesian Active Learning with Partial Batch Label Samplingcited by 0
  10. 2025Active Learning with Task-Driven Representations for Messy Poolscited by 0
  11. 2026When Imbalance Comes Twice: Active Learning under Simulated Class Imbalance and Label Shift in Binary Semantic Segmentationcited by 0
  12. 2026DREAM: Dual-Standard Semantic Homogeneity with Dynamic Optimization for Graph Learning with Label Noisecited by 0
  13. 2026An Approximation Algorithm for Graph Label Selectioncited by 0
  14. 2026Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalancecited by 0
  15. 2026CuBAS: Information Geometric Curvature-Based Adaptive Sampling for Supervised Classificationcited by 0
  16. 2026FunnelAL: Retrieve-then-Rank Active Learning for Single-Class Discoverycited by 0
  17. 2026Overcoming Shortcut Learning in Graph Neural Networks through Active Explanation Guidancecited by 0