mlsanityData to 14 Oct 2026

Bayesian Active Learning by Disagreements: A Geometric Perspective

arXiv 2105.02543 ↗First posted 6 May 2021cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

We present geometric Bayesian active learning by disagreements (GBALD), a framework that performs BALD on its core-set construction interacting with model uncertainty estimation. Technically, GBALD constructs core-set on ellipsoid, not typical sphere, preventing low-representative elements from spherical boundaries. The improvements are twofold: 1) relieve uninformative prior and 2) reduce redundant estimations. Theoretically, geodesic search with ellipsoid can derive tighter lower bound on error and easier to achieve zero error than with sphere. Experiments show that GBALD has slight perturbations to noisy and repeated samples, and outperforms BALD, BatchBALD and other existing deep active learning approaches.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 20 of its 51 references that are in the map. First posted on arXiv 6 May 2021.

Builds on

20 of 51 references.

References · 20

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  3. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  4. 2017Deep Bayesian Active Learning with Image Datacited by 819
  5. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
  6. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 432
  7. 2019Variational Adversarial Active Learningcited by 284
  8. 2020Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learningcited by 210
  9. 2019Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Costcited by 114
  10. 2018Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Studycited by 90
  11. 2018Bayesian Coreset Construction via Greedy Iterative Geodesic Ascentcited by 68
  12. 2019Bayesian Batch Active Learning as Sparse Subset Approximationcited by 68
8 more
  1. 2019Bayesian Generative Active Deep Learningcited by 57
  2. 2017Automated Scalable Bayesian Inference via Hilbert Coresetscited by 55
  3. 2020Differentiating through the Fr'echet Meancited by 53
  4. 2019Learning search spaces for Bayesian optimization: Another view of hyperparameter transfer learningcited by 50
  5. 2017Active Learning for Cost-Sensitive Classificationcited by 41
  6. 2020Finding the Homology of Decision Boundaries with Active Learningcited by 12
  7. 2014Near Optimal Bayesian Active Learning for Decision Makingcited by 10
  8. 2019Deep Bayesian Active Learning for Multiple Correct Outputscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 0; 2023: 3; 2024: 1; 2025: 1; 2026: 3.

9 papers.

  1. 2023In Search of Lost Online Test-time Adaptation: A Surveycited by 44
  2. 2023Deep Active Learning in the Presence of Label Noise: A Surveycited by 5
  3. 2023Active Learning for Object Detection with Non-Redundant Informative Samplingcited by 4
  4. 2024GCI-ViTAL: Gradual Confidence Improvement with Vision Transformers for Active Learning on Label Noisecited by 2
  5. 2026AcquisitionSynthesis: Targeted Data Generation using Acquisition Functionscited by 1
  6. 2021Knowledge-driven Active Learningcited by 0
  7. 2025HeAL3D: Heuristical-enhanced Active Learning for 3D Object Detectioncited by 0
  8. 2026Epistemic Uncertainty for Test-Time Discoverycited by 0
  9. 2026Coverage Aware Active Evaluation for Failure Discovery with Paired Systemscited by 0