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 1111–1120 of 3073 papers

TitleStatusHype
Data-efficient Active Learning for Structured Prediction with Partial Annotation and Self-Training—0
Error-Tolerant Exact Query Learning of Finite Set Partitions with Same-Cluster Oracle—0
On the Limitations of Simulating Active Learning—0
STREAMLINE: Streaming Active Learning for Realistic Multi-Distributional SettingsCode0
Active Learning in Symbolic Regression with Physical Constraints—0
On Dataset Transferability in Active Learning for TransformersCode0
An Active Learning-based Approach for Hosting Capacity Analysis in Distribution Systems—0
Learning to Learn Unlearned Feature for Brain Tumor Segmentation—0
Active Learning For Contextual Linear Optimization: A Margin-Based Approach—0
Sequential Experimental Design for Spectral Measurement: Active Learning Using a Parametric Model—0
Show:102550
← PrevPage 112 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