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 251–260 of 3073 papers

TitleStatusHype
Efficiently Learning at Test-Time: Active Fine-Tuning of LLMsCode2
A Utility-Mining-Driven Active Learning Approach for Analyzing Clickstream Sequences—0
MelissaDL x Breed: Towards Data-Efficient On-line Supervised Training of Multi-parametric Surrogates with Active Learning—0
Interactive Event Sifting using Bayesian Graph Neural Networks—0
Improved detection of discarded fish species through BoxAL active learningCode0
Language Model-Driven Data Pruning Enables Efficient Active Learning—0
STONE: A Submodular Optimization Framework for Active 3D Object DetectionCode0
Structural-Entropy-Based Sample Selection for Efficient and Effective Learning—0
Dual Active Learning for Reinforcement Learning from Human Feedback—0
GPT-4o as the Gold Standard: A Scalable and General Purpose Approach to Filter Language Model Pretraining Data—0
Show:102550
← PrevPage 26 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