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 991–1000 of 3073 papers

TitleStatusHype
Robust online active learning—0
Does Deep Active Learning Work in the Wild?—0
Iterative Loop Method Combining Active and Semi-Supervised Learning for Domain Adaptive Semantic SegmentationCode1
Active Learning-based Domain Adaptive Localized Polynomial Chaos Expansion—0
Few-Shot Image-to-Semantics Translation for Policy Transfer in Reinforcement LearningCode0
Active Learning for Multilingual Semantic Parser—0
Identifying Adversarially Attackable and Robust SamplesCode0
Leveraging Importance Weights in Subset Selection—0
Dual Control of Exploration and Exploitation for Auto-Optimisation Control with Active Learning—0
ActiveLab: Active Learning with Re-Labeling by Multiple Annotators—0
Show:102550
← PrevPage 100 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