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 1871–1880 of 3073 papers

TitleStatusHype
Scaling Gaussian Process Optimization by Evaluating a Few Unique Candidates Multiple Times—0
ScatterSample: Diversified Label Sampling for Data Efficient Graph Neural Network Learning—0
Scholar Inbox: Personalized Paper Recommendations for Scientists—0
SE(3)-Invariant Multiparameter Persistent Homology for Chiral-Sensitive Molecular Property Prediction—0
SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency—0
Search Improves Label for Active Learning—0
Segmentation for Efficient Supervised Language Annotation with an Explicit Cost-Utility Tradeoff—0
SegXAL: Explainable Active Learning for Semantic Segmentation in Driving Scene Scenarios—0
Selecting Syntactic, Non-redundant Segments in Active Learning for Machine Translation—0
An efficient scheme based on graph centrality to select nodes for training for effective learning—0
Show:102550
← PrevPage 188 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