mlsanityData to 7 Oct 2026

Active learning for data streams: a survey

arXiv 2302.08893 ↗First posted 17 Feb 2023stat.ML cs.LG stat.MEcited by 29

Not on the map. Why?

Abstract (arXiv)

Online active learning is a paradigm in machine learning that aims to select the most informative data points to label from a data stream. The problem of minimizing the cost associated with collecting labeled observations has gained a lot of attention in recent years, particularly in real-world applications where data is only available in an unlabeled form. Annotating each observation can be time-consuming and costly, making it difficult to obtain large amounts of labeled data. To overcome this issue, many active learning strategies have been proposed in the last decades, aiming to select the most informative observations for labeling in order to improve the performance of machine learning models. These approaches can be broadly divided into two categories: static pool-based and stream-based active learning. Pool-based active learning involves selecting a subset of observations from a closed pool of unlabeled data, and it has been the focus of many surveys and literature reviews. However, the growing availability of data streams has led to an increase in the number of approaches that focus on online active learning, which involves continuously selecting and labeling observations as they arrive in a stream. This work aims to provide an overview of the most recently proposed approaches for selecting the most informative observations from data streams in real time. We review the various techniques that have been proposed and discuss their strengths and limitations, as well as the challenges and opportunities that exist in this area of research.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 57 of its 246 references that are in the map. First posted on arXiv 17 Feb 2023.

Builds on

57 of 246 references.

References · 57

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2019Large Scale Incremental Learningcited by 727
  5. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  6. 2020A Survey of Deep Active Learningcited by 547
  7. 2020Learning under Concept Drift: A Reviewcited by 470
  8. 2018Online Learning: A Comprehensive Surveycited by 203
  9. 2020Contextual Diversity for Active Learningcited by 139
  10. 2020Cold-start Active Learning through Self-supervised Language Modelingcited by 128
  11. 2021Batch Active Learning at Scalecited by 127
  12. 2014Best-Arm Identification in Linear Banditscited by 98
38 more
  1. 2020Fast active learning for pure exploration in reinforcement learningcited by 92
  2. 2019Sequential Experimental Design for Transductive Linear Banditscited by 88
  3. 2017Learning how to Active Learn: A Deep Reinforcement Learning Approachcited by 79
  4. 2020Active Domain Adaptation via Clustering Uncertainty-weighted Embeddingscited by 71
  5. 2020Optimal Best-arm Identification in Linear Banditscited by 70
  6. 2017Generative Adversarial Active Learningcited by 69
  7. 2021Examining and Combating Spurious Features under Distribution Shiftcited by 64
  8. 2014Minimax Analysis of Active Learningcited by 61
  9. 2020Scalable Active Learning for Object Detectioncited by 58
  10. 2019Bayesian Generative Active Deep Learningcited by 57
  11. 2022Entropy-based Active Learning for Object Detection with Progressive Diversity Constraintcited by 53
  12. 2019Evaluating time series forecasting models: An empirical study on performance estimation methodscited by 52
  13. 2020Linear Bandits with Limited Adaptivity and Learning Distributional Optimal Designcited by 51
  14. 2017A Bayesian Data Augmentation Approach for Learning Deep Modelscited by 50
  15. 2021Online Adaptation to Label Distribution Shiftcited by 44
  16. 2022A survey on learning from imbalanced data streams: taxonomy, challenges, empirical study, and reproducible experimental frameworkcited by 39
  17. 2015Upper-Confidence-Bound Algorithms for Active Learning in Multi-Armed Banditscited by 29
  18. 2022Bayesian Active Learning with Fully Bayesian Gaussian Processescited by 26
  19. 2014Mondrian Forests: Efficient Online Random Forestscited by 25
  20. 2021Stochastic Bandits for Multi-platform Budget Optimization in Online Advertisingcited by 25
  21. 2021Fixed-Budget Best-Arm Identification in Structured Banditscited by 22
  22. 2017Active One-shot Learningcited by 21
  23. 2021Detecting Concept Drift With Neural Network Model Uncertaintycited by 21
  24. 2020Detecting and Adapting to Irregular Distribution Shifts in Bayesian Online Learningcited by 18
  25. 2018Streaming Active Learning Strategies for Real-Life Credit Card Fraud Detection: Assessment and Visualizationcited by 14
  26. 2020Deep Bayesian Active Learning, A Brief Survey on Recent Advancescited by 12
  27. 2019Stochastic Gradient Treescited by 11
  28. 2019Online Active Learning of Reject Option Classifierscited by 9
  29. 2022Stream-based active learning with linear modelscited by 9
  30. 2019Multi-modal Active Learning From Human Data: A Deep Reinforcement Learning Approachcited by 8
  31. 2021Active Weighted Aging Ensemble for Drifted Data Stream Classificationcited by 8
  32. 2017Active Learning for Accurate Estimation of Linear Modelscited by 6
  33. 2021Selective Sampling for Online Best-arm Identificationcited by 6
  34. 2022Online Active Learning for Soft Sensor Development using Semi-Supervised Autoencoderscited by 6
  35. 2016Online Active Linear Regression via Thresholdingcited by 5
  36. 2022TrustAL: Trustworthy Active Learning using Knowledge Distillationcited by 5
  37. 2022Stream-based Active Learning with Verification Latency in Non-stationary Environmentscited by 5
  38. 2023Robust online active learningcited by 5

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 7; 2025: 11; 2026: 9.

29 papers.

Sort:

By area:

  1. 2024A Survey on Deep Active Learning: Recent Advances and New Frontierscited by 53
  2. 2025Drift-aware Collaborative Assistance Mixture of Experts for Heterogeneous Multistream Learningcited by 14
  3. 2024What is the Right Notion of Distance between Predict-then-Optimize Tasks?cited by 2
  4. 2025PB-OEL: A Performance-Bounded Online Ensemble Learning Framework With Mixed Feedback for Real-Time Safety Assessmentcited by 2
  5. 2025Grower-in-the-Loop Interactive Reinforcement Learning for Greenhouse Climate Controlcited by 2
  6. 2023On the Query Strategies for Efficient Online Active Distillationcited by 1
  7. 2023Online Active Learning For Sound Event Detectioncited by 1
  8. 2024From Uncertainty to Clarity: Uncertainty-Guided Class-Incremental Learning for Limited Biomedical Samples via Semantic Expansioncited by 1
  9. 2024MelissaDL x Breed: Towards Data-Efficient On-line Supervised Training of Multi-parametric Surrogates with Active Learningcited by 1
  10. 2024Structuring the Processing Frameworks for Data Stream Evaluation and Applicationcited by 1
  11. 2025A Feedback-Control Framework for Efficient Dataset Collection from In-Vehicle Data Streamscited by 1
  12. 2025How to Purchase Labels? A Cost-Effective Approach Using Active Learning Marketscited by 1
17 more
  1. 2026Learning Where to Simulate: Generative Active Sampling for Online PDE Surrogate Trainingcited by 1
  2. 2024Fair Streaming Feature Selectioncited by 0
  3. 2024Stream-Based Active Learning for Process Monitoringcited by 0
  4. 2025An Efficient Outlier Detection Algorithm for Data Streamingcited by 0
  5. 2025ALPET: Active Few-shot Learning for Citation Worthiness Detection in Low-Resource Wikipedia Languagescited by 0
  6. 2025PEAKS: Selecting Key Training Examples Incrementally via Prediction Error Anchored by Kernel Similaritycited by 0
  7. 2025Metric Matters: A Formal Evaluation of Similarity Measures in Active Learning for Cyber Threat Intelligencecited by 0
  8. 2025An Adaptive Sampling Framework for Detecting Localized Concept Drift under Label Scarcitycited by 0
  9. 2025Data-driven jet fuel demand forecasting: A case study of Copenhagen Airportcited by 0
  10. 2026In-Browser Agents for Search Assistancecited by 0
  11. 2026Adapting Actively on the Fly: Relevance-Guided Online Meta-Learning with Latent Concepts for Geospatial Discoverycited by 0
  12. 2026Feature Weighting Improves Pool-Based Sequential Active Learning for Regressioncited by 0
  13. 2026QueryMarket: Cost-Aware Online Active Learning in Data Marketscited by 0
  14. 2026PinSieve: Production Selective VLM Serving and a Governed Memory Flywheel for Enterprise Content-Quality Triagecited by 0
  15. 2026FuDU: A Fuzzy Dual-dimensional Uncertainty Framework for Streaming Active Learning in Industrial Defect Detectioncited by 0
  16. 2026Candidate Comparability Before Promotion: Conditional Validation in Adaptive Network Intrusion Detectioncited by 0
  17. 2026Label Less, Learn More: Resource-Efficient Active Semi-Supervised Learning for Onboard Satellite Image Annotationcited by 0