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 2676–2700 of 3073 papers

TitleStatusHype
Multi-task Active Learning for Pre-trained Transformer-based ModelsCode0
Differentially Private Active Learning: Balancing Effective Data Selection and PrivacyCode0
Active Sequential Posterior Estimation for Sample-Efficient Simulation-Based InferenceCode0
DiffusAL: Coupling Active Learning with Graph Diffusion for Label-Efficient Node ClassificationCode0
Inferring solutions of differential equations using noisy multi-fidelity dataCode0
XAL: EXplainable Active Learning Makes Classifiers Better Low-resource LearnersCode0
Architectural and Inferential Inductive Biases For Exchangeable Sequence ModelingCode0
Info-Coevolution: An Efficient Framework for Data Model CoevolutionCode0
APRIL: Interactively Learning to Summarise by Combining Active Preference Learning and Reinforcement LearningCode0
Information Condensing Active LearningCode0
A Practical Incremental Learning Framework For Sparse Entity ExtractionCode0
Active Learning via Classifier Impact and Greedy Selection for Interactive Image RetrievalCode0
Black-Box Batch Active Learning for RegressionCode0
Disambiguation of Company names via Deep Recurrent NetworksCode0
DISCERN: Decoding Systematic Errors in Natural Language for Text ClassifiersCode0
Information-Theoretic Active Learning for Content-Based Image RetrievalCode0
Discovering General-Purpose Active Learning StrategiesCode0
Approximate Bayesian Computation with Domain Expert in the LoopCode0
Sampling Bias in Deep Active Classification: An Empirical StudyCode0
Discovery of Self-Assembling π-Conjugated Peptides by Active Learning-Directed Coarse-Grained Molecular SimulationCode0
A-Optimal Active LearningCode0
Bidirectional Uncertainty-Based Active Learning for Open Set AnnotationCode0
Predictive Accuracy-Based Active Learning for Medical Image SegmentationCode0
Discriminative Active LearningCode0
Instance-wise Supervision-level Optimization in Active LearningCode0
Show:102550
← PrevPage 108 of 123Next →

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