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 2901–2950 of 3073 papers

TitleStatusHype
Learning to Multi-Task by Active SamplingCode0
Uncertainty Quantification in Multivariable Regression for Material Property Prediction with Bayesian Neural NetworksCode0
Semi-supervised Active Learning for Video Action DetectionCode0
Fair Active LearningCode0
Fair Active LearningCode0
On the Fragility of Active Learners for Text ClassificationCode0
Fairness Without Harm: An Influence-Guided Active Sampling ApproachCode0
Real-time Safety Assessment of Dynamic Systems in Non-stationary Environments: A Review of Methods and TechniquesCode0
On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise TasksCode0
LSCALE: Latent Space Clustering-Based Active Learning for Node ClassificationCode0
Falcon: Fair Active Learning using Multi-armed BanditsCode0
FAL-CUR: Fair Active Learning using Uncertainty and Representativeness on Fair ClusteringCode0
BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active LearningCode0
Re-Benchmarking Pool-Based Active Learning for Binary ClassificationCode0
Active Learning in Genetic Programming: Guiding Efficient Data Collection for Symbolic RegressionCode0
Survey of Active Learning Hyperparameters: Insights from a Large-Scale Experimental GridCode0
TSceneJAL: Joint Active Learning of Traffic Scenes for 3D Object DetectionCode0
Batch Active Preference-Based Learning of Reward FunctionsCode0
Batch Active Learning Using Determinantal Point ProcessesCode0
Fast and Sample-Efficient Interatomic Neural Network Potentials for Molecules and Materials Based on Gaussian MomentsCode0
Batch Active Learning at ScaleCode0
BaSAL: Size-Balanced Warm Start Active Learning for LiDAR Semantic SegmentationCode0
An Active Approach for Model InterpretationCode0
Active Learning for Neural Machine TranslationCode0
Less is more: sampling chemical space with active learningCode0
BAL: Balancing Diversity and Novelty for Active LearningCode0
Semi-supervised Learning with Deterministic Labeling and Large Margin ProjectionCode0
Amortized Inference for Gaussian Process Hyperparameters of Structured KernelsCode0
On the relationship between calibrated predictors and unbiased volume estimationCode0
Fast post-process Bayesian inference with Variational Sparse Bayesian QuadratureCode0
On the Relationship between Data Efficiency and Error for Uncertainty SamplingCode0
Active Learning with Task Adaptation Pre-training for Speech Emotion RecognitionCode0
Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy LearningCode0
Feature Alignment: Rethinking Efficient Active Learning via Proxy in the Context of Pre-trained ModelsCode0
Active Learning for Manifold Gaussian Process RegressionCode0
Federated Active Learning for Target Domain GeneralisationCode0
Active Learning in CNNs via Expected Improvement MaximizationCode0
Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on Zero-One LossCode0
Feedback Coding for Active LearningCode0
Active^2 Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine TranslationCode0
libact: Pool-based Active Learning in PythonCode0
ALWOD: Active Learning for Weakly-Supervised Object DetectionCode0
Few-Shot Image-to-Semantics Translation for Policy Transfer in Reinforcement LearningCode0
Scalable Batch-Mode Deep Bayesian Active Learning via Equivalence Class AnnealingCode0
Few-Shot Learning with Graph Neural NetworksCode0
Few-Shot Learning with Graph Neural NetworksCode0
Few-shot Named Entity Recognition via Superposition Concept DiscriminationCode0
Active Learning in Bayesian Neural Networks with Balanced Entropy Learning PrincipleCode0
Finding Better Active Learners for Faster Literature ReviewsCode0
Finding Convincing Arguments Using Scalable Bayesian Preference LearningCode0
Show:102550
← PrevPage 59 of 62Next →

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