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 31–40 of 3073 papers

TitleStatusHype
Efficient Deconvolution in Populational Inverse Problems—0
LLM-Guided Taxonomy and Hierarchical Uncertainty for 3D Point CLoud Active Learning—0
Alignment and Safety of Diffusion Models via Reinforcement Learning and Reward Modeling: A Survey—0
Cohort-Based Active Modality Acquisition—0
A Simple Approximation Algorithm for Optimal Decision Tree—0
An active learning framework for multi-group mean estimation—0
Path-integral molecular dynamics with actively-trained and universal machine learning force fieldsCode0
Active Learning on Synthons for Molecular Design—0
Cell Library Characterization for Composite Current Source Models Based on Gaussian Process Regression and Active Learning—0
Designing and Contextualising Probes for African Languages—0
Show:102550
← PrevPage 4 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