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 1421–1430 of 3073 papers

TitleStatusHype
Partition-Based Active Learning for Graph Neural NetworksCode0
Efficient Sampling-Based Bayesian Active Learning for synaptic characterization—0
Batch versus Sequential Active Learning for Recommender Systems—0
PT4AL: Using Self-Supervised Pretext Tasks for Active LearningCode1
Optimizing Active Learning for Low Annotation Budgets—0
Active Learning for Open-set AnnotationCode1
Improving the quality control of seismic data through active learning—0
AcTune: Uncertainty-Aware Active Self-Training for Active Fine-Tuning of Pretrained Language Models—0
Is More Data Better? Using Transformers-Based Active Learning for Efficient and Effective Detection of Abusive Language—0
Improving Data Augmentation in Low-resource Question Answering with Active Learning in Multiple Stages—0
Show:102550
← PrevPage 143 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