# Dropout-based Active Learning for Regression

arXiv: https://arxiv.org/abs/1806.09856 · HTML: https://mlsanity.com/paper/1806.09856/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2018.

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

- [A Framework and Benchmark for Deep Batch Active Learning for Regression](https://mlsanity.com/paper/2203.09410/) (2022)
- [From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimation](https://mlsanity.com/paper/2402.10727/) (2024)
- [Active Learning for Neural PDE Solvers](https://mlsanity.com/paper/2408.01536/) (2024)
- [Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models](https://mlsanity.com/paper/2502.14427/) (2025)
- [Data efficient surrogate modeling for engineering design: Ensemble-free batch mode deep active learning for regression](https://mlsanity.com/paper/2211.10360/) (2022)
- [Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation](https://mlsanity.com/paper/2402.17316/) (2024)
- [Monocular 3D Object Detection with LiDAR Guided Semi Supervised Active Learning](https://mlsanity.com/paper/2307.08415/) (2023)
- [Querying Easily Flip-flopped Samples for Deep Active Learning](https://mlsanity.com/paper/2401.09787/) (2024)
- [Backdoor Attack and Defense for Deep Regression](https://mlsanity.com/paper/2109.02381/) (2021)
- [Active learning for reducing labeling effort in text classification tasks](https://mlsanity.com/paper/2109.04847/) (2021)
- [When Bioprocess Engineering Meets Machine Learning: A Survey from the Perspective of Automated Bioprocess Development](https://mlsanity.com/paper/2209.01083/) (2022)
- [Learning from the Best: Active Learning for Wireless Communications](https://mlsanity.com/paper/2402.04896/) (2024)
- [Bucketized Active Sampling for Learning ACOPF](https://mlsanity.com/paper/2208.07497/) (2022)
- [Scalable Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/2301.05490/) (2023)
- [Crowd-Powered Photo Enhancement Featuring an Active Learning Based Local Filter](https://mlsanity.com/paper/2306.09321/) (2023)
- [Robust and Active Learning for Deep Neural Network Regression](https://mlsanity.com/paper/2107.13124/) (2021)
- [Facilitating automated conversion of scientific knowledge into scientific simulation models with the Machine Assisted Generation, Calibration, and Comparison (MAGCC) Framework](https://mlsanity.com/paper/2204.10382/) (2022)
- [Does Deep Active Learning Work in the Wild?](https://mlsanity.com/paper/2302.00098/) (2023)
- [Benchmarking Active Learning for NILM](https://mlsanity.com/paper/2411.15805/) (2024)
- [Rapid Risk Minimization with Bayesian Models Through Deep Learning Approximation](https://mlsanity.com/paper/2103.15682/) (2021)
- [Towards Robust Deep Active Learning for Scientific Computing](https://mlsanity.com/paper/2201.12632/) (2022)
- [Scalable computation of prediction intervals for neural networks via matrix sketching](https://mlsanity.com/paper/2205.03194/) (2022)
- [Active Learning Framework for Cost-Effective TCR-Epitope Binding Affinity Prediction](https://mlsanity.com/paper/2310.10893/) (2023)
- [Model Uncertainty based Active Learning on Tabular Data using Boosted Trees](https://mlsanity.com/paper/2310.19573/) (2023)

## Abstract (arXiv)

Active learning is relevant and challenging for high-dimensional regression models when the annotation of the samples is expensive. Yet most of the existing sampling methods cannot be applied to large-scale problems, consuming too much time for data processing. In this paper, we propose a fast active learning algorithm for regression, tailored for neural network models. It is based on uncertainty estimation from stochastic dropout output of the network. Experiments on both synthetic and real-world datasets show comparable or better performance (depending on the accuracy metric) as compared to the baselines. This approach can be generalized to other deep learning architectures. It can be used to systematically improve a machine-learning model as it offers a computationally efficient way of sampling additional data.