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 2081–2090 of 3073 papers

TitleStatusHype
Gaussian Process Molecule Property Prediction with FlowMO—0
Gaussian Process Planning with Lipschitz Continuous Reward Functions: Towards Unifying Bayesian Optimization, Active Learning, and Beyond—0
GCI-ViTAL: Gradual Confidence Improvement with Vision Transformers for Active Learning on Label Noise—0
Generalization Bounds and Stopping Rules for Learning with Self-Selected Data—0
Generalized active learning and design of statistical experiments for manifold-valued data—0
Chernoff Sampling for Active Testing and Extension to Active Regression—0
Generalized Coverage for More Robust Low-Budget Active Learning—0
General multi-fidelity surrogate models: Framework and active learning strategies for efficient rare event simulation—0
Generating a Terrain-Robustness Benchmark for Legged Locomotion: A Prototype via Terrain Authoring and Active Learning—0
Generative Active Learning for the Search of Small-molecule Protein Binders—0
Show:102550
← PrevPage 209 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