# Active Learning by Query by Committee with Robust Divergences

arXiv: https://arxiv.org/abs/2211.10013 · HTML: https://mlsanity.com/paper/2211.10013/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 41 references that are in the map.
- First posted on arXiv 18 Nov 2022.

## Builds on (most cited first, 4 of 4)

- [Learning Active Learning from Data](https://mlsanity.com/paper/1703.03365/) (2017)
- [Active Learning: Problem Settings and Recent Developments](https://mlsanity.com/paper/2012.04225/) (2020)
- [Stopping criterion for active learning based on deterministic generalization bounds](https://mlsanity.com/paper/2005.07402/) (2020)
- [Deep Active Learning with Adaptive Acquisition](https://mlsanity.com/paper/1906.11471/) (2019)

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

- [Entropic Open-set Active Learning](https://mlsanity.com/paper/2312.14126/) (2023)
- [Active Learning for Vision-Language Models](https://mlsanity.com/paper/2410.22187/) (2024)
- [Diffusion Active Learning: Towards Data-Driven Experimental Design in Computed Tomography](https://mlsanity.com/paper/2504.03491/) (2025)
- [FisherMask: Enhancing Neural Network Labeling Efficiency in Image Classification Using Fisher Information](https://mlsanity.com/paper/2411.05752/) (2024)
- [StepAL: Step-aware Active Learning for Cataract Surgical Videos](https://mlsanity.com/paper/2507.22059/) (2025)
- [Loss-Driven Bayesian Active Learning](https://mlsanity.com/paper/2604.11995/) (2026)
- [Label-Free Model Failure Detection for Lidar-based Point Cloud Segmentation](https://mlsanity.com/paper/2407.14306/) (2024)
- [Global Context or Local Detail? Adaptive Visual Grounding for Hallucination Mitigation](https://mlsanity.com/paper/2604.24396/) (2026)
- [Projective Maximum Entropy: Universality and Acceptance-Region Calibration](https://mlsanity.com/paper/2607.16547/) (2026)

## Abstract (arXiv)

Active learning is a widely used methodology for various problems with high measurement costs. In active learning, the next object to be measured is selected by an acquisition function, and measurements are performed sequentially. The query by committee is a well-known acquisition function. In conventional methods, committee disagreement is quantified by the Kullback--Leibler divergence. In this paper, the measure of disagreement is defined by the Bregman divergence, which includes the Kullback--Leibler divergence as an instance, and the dual γ-power divergence. As a particular class of the Bregman divergence, the β-divergence is considered. By deriving the influence function, we show that the proposed method using β-divergence and dual γ-power divergence are more robust than the conventional method in which the measure of disagreement is defined by the Kullback--Leibler divergence. Experimental results show that the proposed method performs as well as or better than the conventional method.