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 651–675 of 3073 papers

TitleStatusHype
Batch Selection and Communication for Active Learning with Edge Labeling—0
Generation Of Colors using Bidirectional Long Short Term Memory NetworksCode0
DeMuX: Data-efficient Multilingual LearningCode0
Ulcerative Colitis Mayo Endoscopic Scoring Classification with Active Learning and Generative Data Augmentation—0
Active Mining Sample Pair Semantics for Image-text Matching—0
Dirichlet Active Learning—0
Optimal simulation-based Bayesian decisions—0
Data Distillation for Neural Network Potentials toward Foundational Dataset—0
Active Transfer Learning for Efficient Video-Specific Human Pose EstimationCode1
Army of Thieves: Enhancing Black-Box Model Extraction via Ensemble based sample selectionCode0
Learning to Learn for Few-shot Continual Active Learning—0
Exploring Active Learning in Meta-Learning: Enhancing Context Set Labeling—0
Uncertainty Quantification in Multivariable Regression for Material Property Prediction with Bayesian Neural NetworksCode0
Perturbation-based Active Learning for Question Answering—0
Active Learning-Based Species Range EstimationCode0
Re-weighting Tokens: A Simple and Effective Active Learning Strategy for Named Entity Recognition—0
Incentivized Collaboration in Active Learning—0
Image Restoration with Point Spread Function Regularization and Active Learning—0
Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation—0
Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient SelectionCode1
Model Uncertainty based Active Learning on Tabular Data using Boosted Trees—0
A Planning-and-Exploring Approach to Extreme-Mechanics Force Fields—0
LLMaAA: Making Large Language Models as Active AnnotatorsCode1
A Scalable Training Strategy for Blind Multi-Distribution Noise Removal—0
A Competitive Algorithm for Agnostic Active Learning—0
Show:102550
← PrevPage 27 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