Active Learning

Active Learning is a paradigm in supervised machine learning which uses fewer training examples to achieve better optimization by iteratively training a predictor, and using the predictor in each iteration to choose the training examples which will increase its chances of finding better configurations and at the same time improving the accuracy of the prediction model

Source: Polystore++: Accelerated Polystore System for Heterogeneous Workloads

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 2726–2750 of 3073 papers

Title	Date	Tasks	Status
Does Data Repair Lead to Fair Models? Curating Contextually Fair Data To Reduce Model Bias	Oct 20, 2021	Active LearningAttribute	CodeCode Available
The Label Complexity of Active Learning from Observational Data	May 29, 2019	Active Learningcounterfactual	CodeCode Available
Prioritizing Informative Features and Examples for Deep Learning from Noisy Data	Feb 27, 2024	Active LearningInformativeness	CodeCode Available
Domain Adaptation from Scratch	Sep 2, 2022	Active LearningDomain Adaptation	CodeCode Available
Stream-based Active Learning with Verification Latency in Non-stationary Environments	Apr 14, 2022	Active Learning	CodeCode Available
Interpretable Active Learning	Jul 31, 2017	Active Learning	CodeCode Available
Adaptive Batch Sizes for Active Learning A Probabilistic Numerics Approach	Jun 9, 2023	Active LearningBayesian Optimisation	CodeCode Available
Domain-independent Extraction of Scientific Concepts from Research Articles	Jan 9, 2020	Active LearningArticles	CodeCode Available
Scalable Batch Acquisition for Deep Bayesian Active Learning	Jan 13, 2023	Active Learning	CodeCode Available
Near-Polynomially Competitive Active Logistic Regression	Mar 7, 2025	Active Learningregression	CodeCode Available
An Active Learning Reliability Method for Systems with Partially Defined Performance Functions	Oct 5, 2022	Active LearningAutonomous Driving	CodeCode Available
Intrinsically Motivated Open-Ended Multi-Task Learning Using Transfer Learning to Discover Task Hierarchy	Feb 19, 2021	Active LearningHierarchical Reinforcement Learning	CodeCode Available
Double Q-PID algorithm for mobile robot control	Nov 1, 2018	Active LearningQ-Learning	CodeCode Available
Annotating Data for Fine-Tuning a Neural Ranker? Current Active Learning Strategies are not Better than Random Selection	Sep 12, 2023	Active LearningDomain Adaptation	CodeCode Available
Introspective Learning : A Two-Stage Approach for Inference in Neural Networks	Sep 17, 2022	Active LearningDecision Making	CodeCode Available
Anytime Active Learning	Jul 27, 2014	Active LearningDocument Classification	CodeCode Available
DQI: Measuring Data Quality in NLP	May 2, 2020	Active LearningBenchmarking	CodeCode Available
Uncertainty Estimation of Transformer Predictions for Misclassification Detection	May 1, 2022	Active LearningAdversarial Attack	CodeCode Available
Unsupervised Instance Selection with Low-Label, Supervised Learning for Outlier Detection	Apr 26, 2021	Active LearningOutlier Detection	CodeCode Available
DSAL: Deeply Supervised Active Learning from Strong and Weak Labelers for Biomedical Image Segmentation	Jan 22, 2021	Active LearningEnsemble Learning	CodeCode Available
Towards Regulatory-Confirmed Adaptive Clinical Trials: Machine Learning Opportunities and Solutions	Mar 12, 2025	Active Learning	CodeCode Available
Dual Active Sampling on Batch-Incremental Active Learning	May 22, 2019	Active Learningimage-classification	CodeCode Available
Neural Active Learning on Heteroskedastic Distributions	Nov 2, 2022	Active Learning	CodeCode Available
ScatterShot: Interactive In-context Example Curation for Text Transformation	Feb 14, 2023	Active LearningIn-Context Learning	CodeCode Available
DUAL: Diversity and Uncertainty Active Learning for Text Summarization	Mar 2, 2025	Active LearningDiversity	CodeCode Available

Show:10 25 50

← PrevPage 110 of 123Next →

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	TypiClust	Accuracy	93.2	—	Unverified
2	PT4AL	Accuracy	93.1	—	Unverified
3	Learning loss	Accuracy	91.01	—	Unverified
4	CoreGCN	Accuracy	90.7	—	Unverified
5	Core-set	Accuracy	89.92	—	Unverified
6	Random Baseline (Resnet18)	Accuracy	88.45	—	Unverified
7	Random Baseline (VGG16)	Accuracy	85.09	—	Unverified