# Epistemic Uncertainty Sampling

arXiv: https://arxiv.org/abs/1909.00218 · HTML: https://mlsanity.com/paper/1909.00218/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Aug 2019.

## Built on by (most cited first, 24 of 24)

- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Machine Learning with a Reject Option: A survey](https://mlsanity.com/paper/2107.11277/) (2021)
- [DEUP: Direct Epistemic Uncertainty Prediction](https://mlsanity.com/paper/2102.08501/) (2021)
- [A Comparative Survey of Deep Active Learning](https://mlsanity.com/paper/2203.13450/) (2022)
- [Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernels](https://mlsanity.com/paper/2206.12569/) (2022)
- [Fairness through Aleatoric Uncertainty](https://mlsanity.com/paper/2304.03646/) (2023)
- [Machine Learning for Fraud Detection in E-Commerce: A Research Agenda](https://mlsanity.com/paper/2107.01979/) (2021)
- [ALPBench: A Benchmark for Active Learning Pipelines on Tabular Data](https://mlsanity.com/paper/2406.17322/) (2024)
- [Uncertainty Quantification on Graph Learning: A Survey](https://mlsanity.com/paper/2404.14642/) (2024)
- [Uncertainty Quantification for Machine Learning: One Size Does Not Fit All](https://mlsanity.com/paper/2512.12341/) (2025)
- [Focused Active Learning for Histopathological Image Classification](https://mlsanity.com/paper/2404.04663/) (2024)
- [Adaptive Sampling to Reduce Epistemic Uncertainty Using Prediction Interval-Generation Neural Networks](https://mlsanity.com/paper/2412.10570/) (2024)
- [FAST: Federated Active Learning with Foundation Models for Communication-efficient Sampling and Training](https://mlsanity.com/paper/2504.03783/) (2025)
- [Looking at the posterior: accuracy and uncertainty of neural-network predictions](https://mlsanity.com/paper/2211.14605/) (2022)
- [Context-Based Echo State Networks with Prediction Confidence for Human-Robot Shared Control](https://mlsanity.com/paper/2412.00541/) (2024)
- [Uncertainty Quantification with Proper Scoring Rules: Adjusting Measures to Prediction Tasks](https://mlsanity.com/paper/2505.22538/) (2025)
- [OCSplats: Observation Completeness Quantification and Label Noise Separation in 3DGS](https://mlsanity.com/paper/2508.01239/) (2025)
- [Efficient Credal Prediction through Decalibration](https://mlsanity.com/paper/2603.08495/) (2026)
- [Fair Active Learning: Solving the Labeling Problem in Insurance](https://mlsanity.com/paper/2112.09466/) (2021)
- [Safe AI -- How is this Possible?](https://mlsanity.com/paper/2201.10436/) (2022)
- [Uncertainty Quantification in Deep Neural Networks through Statistical Inference on Latent Space](https://mlsanity.com/paper/2305.10840/) (2023)
- [Model Uncertainty based Active Learning on Tabular Data using Boosted Trees](https://mlsanity.com/paper/2310.19573/) (2023)
- [Active Learning Methods for Efficient Data Utilization and Model Performance Enhancement](https://mlsanity.com/paper/2504.16136/) (2025)
- [Decomposing LLM-Judge Uncertainty to Target Expert Labels](https://mlsanity.com/paper/2609.06444/) (2026)

## Abstract (arXiv)

Various strategies for active learning have been proposed in the machine learning literature. In uncertainty sampling, which is among the most popular approaches, the active learner sequentially queries the label of those instances for which its current prediction is maximally uncertain. The predictions as well as the measures used to quantify the degree of uncertainty, such as entropy, are almost exclusively of a probabilistic nature. In this paper, we advocate a distinction between two different types of uncertainty, referred to as epistemic and aleatoric, in the context of active learning. Roughly speaking, these notions capture the reducible and the irreducible part of the total uncertainty in a prediction, respectively. We conjecture that, in uncertainty sampling, the usefulness of an instance is better reflected by its epistemic than by its aleatoric uncertainty. This leads us to suggest the principle of "epistemic uncertainty sampling", which we instantiate by means of a concrete approach for measuring epistemic and aleatoric uncertainty. In experimental studies, epistemic uncertainty sampling does indeed show promising performance.