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 821–830 of 3073 papers

TitleStatusHype
Direct Acquisition Optimization for Low-Budget Active Learning—0
An Artificial Intelligence (AI) workflow for catalyst design and optimization—0
Empowering Language Models with Active Inquiry for Deeper Understanding—0
Enhanced sampling of robust molecular datasets with uncertainty-based collective variables—0
Information-Theoretic Active Correlation Clustering—0
Active Learning for Graphs with Noisy Structures—0
Foundation Model Makes Clustering A Better Initialization For Cold-Start Active LearningCode0
Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical GuaranteesCode0
Deep Active Learning for Data Mining from Conflict Text Corpora—0
Conditional Normalizing Flows for Active Learning of Coarse-Grained Molecular RepresentationsCode0
Show:102550
← PrevPage 83 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