# Stopping Criterion for Active Learning Based on Error Stability

arXiv: https://arxiv.org/abs/2104.01836 · HTML: https://mlsanity.com/paper/2104.01836/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 50 references that are in the map.
- First posted on arXiv 5 Apr 2021.

## Builds on (most cited first, 12 of 12)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [A Primer on PAC-Bayesian Learning](https://mlsanity.com/paper/1901.05353/) (2019)
- [Learning Active Learning from Data](https://mlsanity.com/paper/1703.03365/) (2017)
- [PAC-Bayesian Theory Meets Bayesian Inference](https://mlsanity.com/paper/1605.08636/) (2016)
- [Simpler PAC-Bayesian Bounds for Hostile Data](https://mlsanity.com/paper/1610.07193/) (2016)
- [Active Learning: Problem Settings and Recent Developments](https://mlsanity.com/paper/2012.04225/) (2020)
- [A Method for Stopping Active Learning Based on Stabilizing Predictions and the Need for User-Adjustable Stopping](https://mlsanity.com/paper/1409.5165/) (2014)
- [Stopping criterion for active learning based on deterministic generalization bounds](https://mlsanity.com/paper/2005.07402/) (2020)
- [MaxiMin Active Learning in Overparameterized Model Classes}](https://mlsanity.com/paper/1905.12782/) (2019)
- [Stopping Active Learning based on Predicted Change of F Measure for Text Classification](https://mlsanity.com/paper/1901.09118/) (2019)
- [Analysis of Stopping Active Learning based on Stabilizing Predictions](https://mlsanity.com/paper/1504.06329/) (2015)

## Built on by (most cited first, 6 of 6)

- [Hitting the Target: Stopping Active Learning at the Cost-Based Optimum](https://mlsanity.com/paper/2110.03802/) (2021)
- [Smooth Sailing: Improving Active Learning for Pre-trained Language Models with Representation Smoothness Analysis](https://mlsanity.com/paper/2212.11680/) (2022)
- [Finding Needles in the Haystack: Transductive Active Labeling in Ecology](https://mlsanity.com/paper/2606.03821/) (2026)
- [Bayesian inference of composition-dependent phase diagrams](https://mlsanity.com/paper/2309.01271/) (2023)
- [Reciprocal Learning](https://mlsanity.com/paper/2408.06257/) (2024)
- [Learnable Weighting of Intra-Attribute Distances for Categorical Data Clustering with Nominal and Ordinal Attributes](https://mlsanity.com/paper/2607.05464/) (2026)

## Abstract (arXiv)

Active learning is a framework for supervised learning to improve the predictive performance by adaptively annotating a small number of samples. To realize efficient active learning, both an acquisition function that determines the next datum and a stopping criterion that determines when to stop learning should be considered. In this study, we propose a stopping criterion based on error stability, which guarantees that the change in generalization error upon adding a new sample is bounded by the annotation cost and can be applied to any Bayesian active learning. We demonstrate that the proposed criterion stops active learning at the appropriate timing for various learning models and real datasets.