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 491–500 of 3073 papers

TitleStatusHype
Active Output Selection Strategies for Multiple Learning Regression Models—0
Active partitioning: inverting the paradigm of active learning—0
Active Perceptual Similarity Modeling with Auxiliary Information—0
Active PETs: Active Data Annotation Prioritisation for Few-Shot Claim Verification with Pattern Exploiting Training—0
Active Learning Over Multiple Domains in Natural Language Tasks—0
Active Learning over DNN: Automated Engineering Design Optimization for Fluid Dynamics Based on Self-Simulated Dataset—0
Active Preference Learning for Large Language Models—0
Active Learning for Graph Neural Networks via Node Feature Propagation—0
NE-LP: Normalized Entropy and Loss Prediction based Sampling for Active Learning in Chinese Word Segmentation on EHRs—0
A Survey on Curriculum Learning—0
Show:102550
← PrevPage 50 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