SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2826–2850 of 3073 papers

TitleStatusHype
Onception: Active Learning with Expert Advice for Real World Machine TranslationCode0
Enhancing Semi-supervised Domain Adaptation via Effective Target LabelingCode0
Enhancing Semi-Supervised Learning via Representative and Diverse Sample SelectionCode0
Enhancing Text Classification through LLM-Driven Active Learning and Human AnnotationCode0
Active Preference Optimization for Sample Efficient RLHFCode0
Enhancing Treatment Effect Estimation via Active Learning: A Counterfactual Covering PerspectiveCode0
On Dataset Transferability in Active Learning for TransformersCode0
Proximity-Based Active Learning on Streaming Data: A Personalized Eating Moment RecognitionCode0
Entity Alignment with Noisy Annotations from Large Language ModelsCode0
Training Ensembles with Inliers and Outliers for Semi-supervised Active LearningCode0
The Unreasonable Effectiveness of Noisy Data for Fine-Grained RecognitionCode0
Bayesian active learning for optimization and uncertainty quantification in protein dockingCode0
Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual PersistenceCode0
Active Learning of Spin Network ModelsCode0
Learning Active Learning from DataCode0
On Efficiently Acquiring Annotations for Multilingual ModelsCode0
Active Learning of Molecular Data for Task-Specific ObjectivesCode0
Training-Free Neural Active Learning with Initialization-Robustness GuaranteesCode0
ESA: Annotation-Efficient Active Learning for Semantic SegmentationCode0
Training Greedy Policy for Proposal Batch Selection in Expensive Multi-Objective Combinatorial OptimizationCode0
Learning atomic forces from uncertainty-calibrated adversarial attacksCode0
On Graph Neural Network Ensembles for Large-Scale Molecular Property PredictionCode0
ET-AL: Entropy-Targeted Active Learning for Bias Mitigation in Materials DataCode0
On Initial Pools for Deep Active LearningCode0
An Active Learning-Based Streaming Pipeline for Reduced Data Training of Structure Finding Models in Neutron DiffractometryCode0
Show:102550
← PrevPage 114 of 123Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TypiClustAccuracy93.2—Unverified
2PT4ALAccuracy93.1—Unverified
3Learning lossAccuracy91.01—Unverified
4CoreGCNAccuracy90.7—Unverified
5Core-setAccuracy89.92—Unverified
6Random Baseline (Resnet18)Accuracy88.45—Unverified
7Random Baseline (VGG16)Accuracy85.09—Unverified