mlsanityData to 7 Oct 2026

Prediction-Oriented Bayesian Active Learning

arXiv 2304.08151 ↗First posted 17 Apr 2023cs.LG stat.MLcited by 60

Not on the map. Why?

Abstract (arXiv)

Information-theoretic approaches to active learning have traditionally focused on maximising the information gathered about the model parameters, most commonly by optimising the BALD score. We highlight that this can be suboptimal from the perspective of predictive performance. For example, BALD lacks a notion of an input distribution and so is prone to prioritise data of limited relevance. To address this we propose the expected predictive information gain (EPIG), an acquisition function that measures information gain in the space of predictions rather than parameters. We find that using EPIG leads to stronger predictive performance compared with BALD across a range of datasets and models, and thus provides an appealing drop-in replacement.

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). Builds on 34 of its 81 references that are in the map. First posted on arXiv 17 Apr 2023.

Builds on

34 of 81 references.

References · 34

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  6. 2018Reconciling modern machine learning practice and the bias-variance trade-offcited by 919
  7. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  8. 2017Deep Bayesian Active Learning with Image Datacited by 812
  9. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  10. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  11. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  12. 2014Scalable Variational Gaussian Process Classificationcited by 226
22 more
  1. 2014Predictive Entropy Search for Efficient Global Optimization of Black-box Functionscited by 201
  2. 2023Modern Bayesian Experimental Designcited by 121
  3. 2019Variational Bayesian Optimal Experimental Designcited by 116
  4. 2017Deep Active Learning for Named Entity Recognitioncited by 108
  5. 2017Noisy Natural Gradient as Variational Inferencecited by 94
  6. 2018Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Studycited by 90
  7. 2017On Nesting Monte Carlo Estimatorscited by 82
  8. 2019Bayesian Batch Active Learning as Sparse Subset Approximationcited by 68
  9. 2022Do Bayesian Neural Networks Need To Be Fully Stochastic?cited by 63
  10. 2021Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answeringcited by 62
  11. 2019Bayesian Generative Active Deep Learningcited by 57
  12. 2020Towards Robust and Reproducible Active Learning Using Neural Networkscited by 53
  13. 2018Differentiable Compositional Kernel Learning for Gaussian Processescited by 23
  14. 2021Diversity Enhanced Active Learning with Strictly Proper Scoring Rulescited by 22
  15. 2020Beyond Marginal Uncertainty: How Accurately can Bayesian Regression Models Estimate Posterior Predictive Correlations?cited by 21
  16. 2019Active Learning for Decision-Making from Imbalanced Observational Datacited by 16
  17. 2020Bayesian active learning for production, a systematic study and a reusable librarycited by 15
  18. 2021Targeted Active Learning for Bayesian Decision-Makingcited by 12
  19. 2017Improving drug sensitivity predictions in precision medicine through active expert knowledge elicitationcited by 8
  20. 2016Knowledge Elicitation via Sequential Probabilistic Inference for High-Dimensional Predictioncited by 5
  21. 2019Human-in-the-loop Active Covariance Learning for Improving Prediction in Small Data Setscited by 2
  22. 2015Estimating Optimal Active Learning via Model Retraining Improvementcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 15; 2025: 17; 2026: 24.

60 papers.

Sort:

By area:

  1. 2024Rethinking Aleatoric and Epistemic Uncertaintycited by 40
  2. 2025BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Designcited by 21
  3. 2024CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-trainingcited by 20
  4. 2024Amortized Bayesian Experimental Design for Decision-Makingcited by 20
  5. 2024Deep Bayesian Active Learning for Preference Modeling in Large Language Modelscited by 19
  6. 2024On Subjective Uncertainty Quantification and Calibration in Natural Language Generationcited by 14
  7. 2024Post-hoc Probabilistic Vision-Language Modelscited by 13
  8. 2023DiscoBAX: Discovery of Optimal Intervention Sets in Genomic Experiment Designcited by 12
  9. 2024Nesting Particle Filters for Experimental Design in Dynamical Systemscited by 12
  10. 2024Making Better Use of Unlabelled Data in Bayesian Active Learningcited by 10
  11. 2023Variational Sequential Optimal Experimental Design using Reinforcement Learningcited by 8
  12. 2024Active Fine-Tuning of Multi-Task Policiescited by 8
38 more
  1. 2025ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisitioncited by 8
  2. 2023Deep Stochastic Processes via Functional Markov Transition Operatorscited by 7
  3. 2024Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitionscited by 7
  4. 2026Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world modelscited by 6
  5. 2024Streamlining Prediction in Bayesian Deep Learningcited by 5
  6. 2024Improving Active Learning with a Bayesian Representation of Epistemic Uncertaintycited by 4
  7. 2025Active Learning with Selective Time-Step Acquisition for PDEscited by 4
  8. 2025Distributionally Robust Active Learning for Gaussian Process Regressioncited by 3
  9. 2025Distributional Training Data Attribution: What do Influence Functions Sample?cited by 3
  10. 2023Enhancing Trustworthiness in ML-Based Network Intrusion Detection with Uncertainty Quantificationcited by 2
  11. 2024Bayesian Active Learning for Censored Regressioncited by 2
  12. 2024Active Few-Shot Fine-Tuningcited by 2
  13. 2025BioBO: Biology-informed Bayesian Optimization for Perturbation Designcited by 2
  14. 2025Causal-EPIG: A Prediction-Oriented Active Learning Framework for CATE Estimationcited by 2
  15. 2025Accelerated Learning on Large Scale Screens using Generative Library Modelscited by 2
  16. 2025Informed Initialization for Bayesian Optimization and Active Learningcited by 2
  17. 2026Cold-Start Personalization via Training-Free Priors from Structured World Modelscited by 2
  18. 2026Constrained Bayesian Experimental Design via Online Planningcited by 2
  19. 2026Efficient Adaptive Data Acquisition via Pretrained Belief Representationscited by 2
  20. 2025Trust Me, I Know the Way: Predictive Uncertainty in the Presence of Shortcut Learningcited by 1
  21. 2025Goal-Oriented Sequential Bayesian Experimental Design for Causal Learningcited by 1
  22. 2025An Interactive Framework for Finding the Optimal Trade-off in Differential Privacycited by 1
  23. 2025ActiveCQ: Active Estimation of Causal Quantitiescited by 1
  24. 2025Deep Ensembles for Epistemic Uncertainty: A Frequentist Perspectivecited by 1
  25. 2026Team, Then Trim: An Assembly-Line LLM Framework for High-Quality Tabular Data Generationcited by 1
  26. 2026Observationally Informed Adaptive Causal Experimental Designcited by 1
  27. 2026Loss-Driven Bayesian Active Learningcited by 1
  28. 2026Active Real-World Factor-Based Evaluation for Generalist Robot Policiescited by 1
  29. 2024Towards Dynamic Feature Acquisition on Medical Time Series by Maximizing Conditional Mutual Informationcited by 0
  30. 2025Prediction-Oriented Subsampling from Data Streamscited by 0
  31. 2025Batch Bayesian Active Learning with Partial Batch Label Samplingcited by 0
  32. 2025Active Learning with Task-Driven Representations for Messy Poolscited by 0
  33. 2026Correcting Boundary Bias and Observation Independence in Bayesian Experimental Designcited by 0
  34. 2026Active Transfer Bagging: A New Approach for Accelerated Active Learning Acquisition of Data by Combined Transfer Learning and Bagging Based Modelscited by 0
  35. 2026Pragmatic Curiosity: A Unified Framework for Hybrid Learning and Optimization via Active Inferencecited by 0
  36. 2026Goal-Oriented Influence-Maximizing Data Acquisition for Learning and Optimizationcited by 0
  37. 2026Point-Identification of a Robust Predictor Under Latent Shift with Imperfect Proxiescited by 0
  38. 2026Active Learning for Gaussian Process Regression Under Self-Induced Boltzmann Weightscited by 0

50 most cited of 60 All 60 (JSON)