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 951–975 of 3073 papers

TitleStatusHype
A Histopathology Study Comparing Contrastive Semi-Supervised and Fully Supervised Learning—0
Bayesian Quadrature Optimization for Probability Threshold Robustness Measure—0
Bayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learning—0
Bayesian Semisupervised Learning with Deep Generative Models—0
Active metric learning and classification using similarity queries—0
BayesOpt: A Library for Bayesian optimization with Robotics Applications—0
Bayes-Optimal Entropy Pursuit for Active Choice-Based Preference Learning—0
Beating the Minimax Rate of Active Learning with Prior Knowledge—0
A Graph-Based Approach for Active Learning in Regression—0
Benchmarking Active Learning for NILM—0
Benchmarking Active Learning Strategies for Materials Optimization and Discovery—0
Benchmarking Multi-Domain Active Learning on Image Classification—0
Active Learning for Event Extraction with Memory-based Loss Prediction Model—0
Active learning for structural reliability analysis with multiple limit state functions through variance-enhanced PC-Kriging surrogate models—0
Benchmarks and Algorithms for Offline Preference-Based Reward Learning—0
Agnostic Multi-Group Active Learning—0
BERT-PersNER: A New Model for Persian Named Entity Recognition—0
Best Arm Identification for Contaminated Bandits—0
Best Practices in Pool-based Active Learning for Image Classification—0
Better Optimization can Reduce Sample Complexity: Active Semi-Supervised Learning via Convergence Rate Control—0
Beyond Accuracy: ROI-driven Data Analytics of Empirical Data—0
Beyond Active Learning: Leveraging the Full Potential of Human Interaction via Auto-Labeling, Human Correction, and Human Verification—0
Beyond Comparing Image Pairs: Setwise Active Learning for Relative Attributes—0
Beyond Disagreement-based Agnostic Active Learning—0
Agnostic Active Learning Without Constraints—0
Show:102550
← PrevPage 39 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