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 171–180 of 3073 papers

TitleStatusHype
Active Reinforcement Learning Strategies for Offline Policy Improvement—0
AutoSciLab: A Self-Driving Laboratory For Interpretable Scientific Discovery—0
Active Large Language Model-based Knowledge Distillation for Session-based Recommendation—0
ABC3: Active Bayesian Causal Inference with Cohn Criteria in Randomized ExperimentsCode0
From Easy to Hard: Progressive Active Learning Framework for Infrared Small Target Detection with Single Point SupervisionCode3
An Active Parameter Learning Approach to The Identification of Safe Regions—0
The Cost of Replicability in Active Learning—0
Congruence-based Learning of Probabilistic Deterministic Finite Automata—0
Safe Active Learning for Gaussian Differential Equations—0
Enhancing Modality Representation and Alignment for Multimodal Cold-start Active Learning—0
Show:102550
← PrevPage 18 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