mlsanityData to 7 Oct 2026

BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning

arXiv 1906.08158 ↗First posted 19 Jun 2019cs.LG stat.MLcited by 428

Not on the map. Why?

Abstract (arXiv)

We develop BatchBALD, a tractable approximation to the mutual information between a batch of points and model parameters, which we use as an acquisition function to select multiple informative points jointly for the task of deep Bayesian active learning. BatchBALD is a greedy linear-time 1 - frac1e-approximate algorithm amenable to dynamic programming and efficient caching. We compare BatchBALD to the commonly used approach for batch data acquisition and find that the current approach acquires similar and redundant points, sometimes performing worse than randomly acquiring data. We finish by showing that, using BatchBALD to consider dependencies within an acquisition batch, we achieve new state of the art performance on standard benchmarks, providing substantial data efficiency improvements in batch acquisition.

Key facts. Cited by 428 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 76; 2022: 85; 2023: 84; 2024: 75; 2025: 61; 2026: 46.

428 papers.

Sort:

By area:

  1. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  2. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 384
  3. 2022Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learntcited by 233
  4. 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
  5. 2021Active Learning by Acquiring Contrastive Examplescited by 154
  6. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 131
  7. 2021Batch Active Learning at Scalecited by 127
  8. 2023Modern Bayesian Experimental Designcited by 121
  9. 2021Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Taskscited by 100
  10. 2021Gone Fishing: Neural Active Learning with Fisher Embeddingscited by 88
  11. 2022A Comparative Survey of Deep Active Learningcited by 88
  12. 2021On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertaintycited by 87
38 more
  1. 2023Anchor Points: Benchmarking Models with Much Fewer Examplescited by 84
  2. 2021SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarioscited by 83
  3. 2021Active Testing: Sample-Efficient Model Evaluationcited by 82
  4. 2021Active Learning for Deep Object Detection via Probabilistic Modelingcited by 79
  5. 2022Efficient Methods for Natural Language Processing: A Surveycited by 78
  6. 2021On Statistical Bias In Active Learning: How and When To Fix Itcited by 72
  7. 2023FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Informationcited by 63
  8. 2022Active Learning Through a Covering Lenscited by 62
  9. 2023Prediction-Oriented Bayesian Active Learningcited by 60
  10. 2024Active Preference Learning for Large Language Modelscited by 55
  11. 2024A Survey on Deep Active Learning: Recent Advances and New Frontierscited by 53
  12. 2021ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentationcited by 52
  13. 2023Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimescited by 52
  14. 2021Improving black-box optimization in VAE latent space using decoder uncertaintycited by 51
  15. 2022Interventions, Where and How? Experimental Design for Causal Models at Scalecited by 49
  16. 2022A Framework and Benchmark for Deep Batch Active Learning for Regressioncited by 47
  17. 2022FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clientscited by 46
  18. 2021Active label cleaning for improved dataset quality under resource constraintscited by 44
  19. 2024Rethinking Aleatoric and Epistemic Uncertaintycited by 40
  20. 2021Effective Evaluation of Deep Active Learning on Image Classification Taskscited by 37
  21. 2022Submodularity In Machine Learning and Artificial Intelligencecited by 37
  22. 2021Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learningcited by 36
  23. 2023Explaining Predictive Uncertainty with Information Theoretic Shapley Valuescited by 36
  24. 2021Deep Active Learning by Leveraging Training Dynamicscited by 32
  25. 2023A comprehensive survey on deep active learning in medical image analysiscited by 32
  26. 2021On the Importance of Effectively Adapting Pretrained Language Models for Active Learningcited by 31
  27. 2022Computer-Aided Multi-Objective Optimization in Small Molecule Discoverycited by 31
  28. 2024PINNACLE: PINN Adaptive ColLocation and Experimental points selectioncited by 31
  29. 2022Active Learning for Optimal Intervention Design in Causal Modelscited by 30
  30. 2021Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximizationcited by 28
  31. 2022Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantitiescited by 28
  32. 2021Data Shapley Valuation for Efficient Batch Active Learningcited by 27
  33. 2021Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detectioncited by 27
  34. 2021Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Datacited by 27
  35. 2021TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Informationcited by 27
  36. 2022Bayesian Active Learning with Fully Bayesian Gaussian Processescited by 26
  37. 2022In Defense of Core-set: A Density-aware Core-set Selection for Active Learningcited by 26
  38. 2023Exploring Active 3D Object Detection from a Generalization Perspectivecited by 26

50 most cited of 428 All 428 (JSON)