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 221–230 of 3073 papers

TitleStatusHype
FisherMask: Enhancing Neural Network Labeling Efficiency in Image Classification Using Fisher InformationCode0
Performance-Guided LLM Knowledge Distillation for Efficient Text Classification at Scale—0
Hands-On Tutorial: Labeling with LLM and Human-in-the-Loop—0
Constrained Multi-objective Bayesian Optimization through Optimistic Constraints EstimationCode0
An information-matching approach to optimal experimental design and active learning—0
Exploiting Contextual Uncertainty of Visual Data for Efficient Training of Deep Models—0
Machine Learning-Accelerated Multi-Objective Design of Fractured Geothermal SystemsCode0
Cost-Aware Query Policies in Active Learning for Efficient Autonomous Robotic Exploration—0
SpiroActive: Active Learning for Efficient Data Acquisition for Spirometry—0
Active Learning for Vision-Language Models—0
Show:102550
← PrevPage 23 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