# Bayesian Active Learning by Disagreements: A Geometric Perspective

arXiv: https://arxiv.org/abs/2105.02543 · HTML: https://mlsanity.com/paper/2105.02543/

## 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 (most cited first, 20 of 20)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning](https://mlsanity.com/paper/2002.06470/) (2020)
- [Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost](https://mlsanity.com/paper/1910.07153/) (2019)
- [Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Study](https://mlsanity.com/paper/1808.05697/) (2018)
- [Bayesian Coreset Construction via Greedy Iterative Geodesic Ascent](https://mlsanity.com/paper/1802.01737/) (2018)
- [Bayesian Batch Active Learning as Sparse Subset Approximation](https://mlsanity.com/paper/1908.02144/) (2019)
- [Bayesian Generative Active Deep Learning](https://mlsanity.com/paper/1904.11643/) (2019)
- [Automated Scalable Bayesian Inference via Hilbert Coresets](https://mlsanity.com/paper/1710.05053/) (2017)
- [Differentiating through the Fr'echet Mean](https://mlsanity.com/paper/2003.00335/) (2020)
- [Learning search spaces for Bayesian optimization: Another view of hyperparameter transfer learning](https://mlsanity.com/paper/1909.12552/) (2019)
- [Active Learning for Cost-Sensitive Classification](https://mlsanity.com/paper/1703.01014/) (2017)
- [Finding the Homology of Decision Boundaries with Active Learning](https://mlsanity.com/paper/2011.09645/) (2020)
- [Near Optimal Bayesian Active Learning for Decision Making](https://mlsanity.com/paper/1402.5886/) (2014)
- [Deep Bayesian Active Learning for Multiple Correct Outputs](https://mlsanity.com/paper/1912.01119/) (2019)

## Built on by (most cited first, 9 of 9)

- [In Search of Lost Online Test-time Adaptation: A Survey](https://mlsanity.com/paper/2310.20199/) (2023)
- [Deep Active Learning in the Presence of Label Noise: A Survey](https://mlsanity.com/paper/2302.11075/) (2023)
- [Active Learning for Object Detection with Non-Redundant Informative Sampling](https://mlsanity.com/paper/2307.08414/) (2023)
- [GCI-ViTAL: Gradual Confidence Improvement with Vision Transformers for Active Learning on Label Noise](https://mlsanity.com/paper/2411.05939/) (2024)
- [AcquisitionSynthesis: Targeted Data Generation using Acquisition Functions](https://mlsanity.com/paper/2605.13149/) (2026)
- [Knowledge-driven Active Learning](https://mlsanity.com/paper/2110.08265/) (2021)
- [HeAL3D: Heuristical-enhanced Active Learning for 3D Object Detection](https://mlsanity.com/paper/2505.00507/) (2025)
- [Epistemic Uncertainty for Test-Time Discovery](https://mlsanity.com/paper/2605.11328/) (2026)
- [Coverage Aware Active Evaluation for Failure Discovery with Paired Systems](https://mlsanity.com/paper/2608.13719/) (2026)

## 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.