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 601–625 of 3073 papers

TitleStatusHype
CFlowNets: Continuous Control with Generative Flow NetworksCode0
Accelerating materials discovery for polymer solar cells: Data-driven insights enabled by natural language processingCode0
Characterizing the robustness of Bayesian adaptive experimental designs to active learning biasCode0
Class Balance Matters to Active Class-Incremental LearningCode0
Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical GuaranteesCode0
Building a comprehensive syntactic and semantic corpus of Chinese clinical textsCode0
Breaking the Barrier: Selective Uncertainty-based Active Learning for Medical Image SegmentationCode0
Active learning for reducing labeling effort in text classification tasksCode0
A Flexible Framework for Anomaly Detection via Dimensionality ReductionCode0
Buy Me That Look: An Approach for Recommending Similar Fashion ProductsCode0
Black-Box Batch Active Learning for RegressionCode0
Active Learning for Semantic Segmentation with Multi-class Label QueryCode0
Boolean matrix logic programming for active learning of gene functions in genome-scale metabolic network modelsCode0
Annotating Data for Fine-Tuning a Neural Ranker? Current Active Learning Strategies are not Better than Random SelectionCode0
Calpric: Inclusive and Fine-grain Labeling of Privacy Policies with Crowdsourcing and Active LearningCode0
Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning ArchitectureCode0
Bayesian Semi-supervised Learning with Graph Gaussian ProcessesCode0
Constraining the Parameters of High-Dimensional Models with Active LearningCode0
Continual Active Learning Using Pseudo-Domains for Limited Labelling Resources and Changing Acquisition CharacteristicsCode0
Continual Deep Active Learning for Medical Imaging: Replay-Base Architecture for Context AdaptationCode0
Active Learning amidst Logical KnowledgeCode0
Controllable Textual Inversion for Personalized Text-to-Image GenerationCode0
Benchmarking of Query Strategies: Towards Future Deep Active LearningCode0
Cost-Effective Active Learning for Melanoma SegmentationCode0
Beyond Marginal Uncertainty: How Accurately can Bayesian Regression Models Estimate Posterior Predictive Correlations?Code0
Show:102550
← PrevPage 25 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