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 2301–2310 of 3073 papers

TitleStatusHype
Deep Reinforcement Active Learning for Human-in-the-Loop Person Re-Identification—0
Active Anomaly Detection for time-domain discoveries—0
Noisy Batch Active Learning with Deterministic AnnealingCode0
Data-driven discovery of free-form governing differential equations—0
Active Learning for Event Detection in Support of Disaster Analysis Applications—0
Consistency-Based Semi-Supervised Active Learning: Towards Minimizing Labeling Budget—0
Omnibus Dropout for Improving The Probabilistic Classification Outputs of ConvNets—0
Training Data Distribution Search with Ensemble Active Learning—0
Transfer Active Learning For Graph Neural Networks—0
Active Learning Graph Neural Networks via Node Feature Propagation—0
Show:102550
← PrevPage 231 of 308Next →

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