mlsanityData to 7 Oct 2026

Dropout-based Active Learning for Regression

arXiv 1806.09856 ↗First posted 26 Jun 2018cs.LG stat.MLcited by 24

Not on the map. Why?

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.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 7; 2023: 6; 2024: 6; 2025: 1.

24 papers.

Sort:

  1. 2022A Framework and Benchmark for Deep Batch Active Learning for Regressioncited by 47
  2. 2024From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimationcited by 27
  3. 2024Active Learning for Neural PDE Solverscited by 22
  4. 2025Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Modelscited by 18
  5. 2022Data efficient surrogate modeling for engineering design: Ensemble-free batch mode deep active learning for regressioncited by 11
  6. 2024Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillationcited by 11
  7. 2023Monocular 3D Object Detection with LiDAR Guided Semi Supervised Active Learningcited by 10
  8. 2024Querying Easily Flip-flopped Samples for Deep Active Learningcited by 7
  9. 2021Backdoor Attack and Defense for Deep Regressioncited by 6
  10. 2021Active learning for reducing labeling effort in text classification taskscited by 4
  11. 2022When Bioprocess Engineering Meets Machine Learning: A Survey from the Perspective of Automated Bioprocess Developmentcited by 4
  12. 2024Learning from the Best: Active Learning for Wireless Communicationscited by 4
12 more
  1. 2022Bucketized Active Sampling for Learning ACOPFcited by 3
  2. 2023Scalable Batch Acquisition for Deep Bayesian Active Learningcited by 2
  3. 2023Crowd-Powered Photo Enhancement Featuring an Active Learning Based Local Filtercited by 2
  4. 2021Robust and Active Learning for Deep Neural Network Regressioncited by 1
  5. 2022Facilitating automated conversion of scientific knowledge into scientific simulation models with the Machine Assisted Generation, Calibration, and Comparison (MAGCC) Frameworkcited by 1
  6. 2023Does Deep Active Learning Work in the Wild?cited by 1
  7. 2024Benchmarking Active Learning for NILMcited by 1
  8. 2021Rapid Risk Minimization with Bayesian Models Through Deep Learning Approximationcited by 0
  9. 2022Towards Robust Deep Active Learning for Scientific Computingcited by 0
  10. 2022Scalable computation of prediction intervals for neural networks via matrix sketchingcited by 0
  11. 2023Active Learning Framework for Cost-Effective TCR-Epitope Binding Affinity Predictioncited by 0
  12. 2023Model Uncertainty based Active Learning on Tabular Data using Boosted Treescited by 0