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 1921–1930 of 3073 papers

TitleStatusHype
Efficient active learning of sparse halfspaces—0
Efficient active learning of sparse halfspaces with arbitrary bounded noise—0
Efficient Active Learning with Abstention—0
Efficient and Parsimonious Agnostic Active Learning—0
Efficient and Reliable Probabilistic Interactive Learning with Structured Outputs—0
Efficient Argument Structure Extraction with Transfer Learning and Active Learning—0
Efficient Auto-Labeling of Large-Scale Poultry Datasets (ALPD) Using Semi-Supervised Models, Active Learning, and Prompt-then-Detect Approach—0
Efficient Biological Data Acquisition through Inference Set Design—0
Efficient Classifier Training to Minimize False Merges in Electron Microscopy Segmentation—0
Efficient Data Selection for Training Genomic Perturbation Models—0
Show:102550
← PrevPage 193 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