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 251–300 of 3073 papers

TitleStatusHype
A unified framework for closed-form nonparametric regression, classification, preference and mixed problems with Skew Gaussian ProcessesCode1
Enhanced spatio-temporal electric load forecasts using less data with active deep learningCode1
What Makes a "Good" Data Augmentation in Knowledge Distillation -- A Statistical PerspectiveCode1
Counting People by Estimating People FlowsCode1
Uncertainty estimation for molecular dynamics and samplingCode1
Active Learning for BERT: An Empirical StudyCode1
Active Learning for Human-in-the-Loop Customs InspectionCode1
Semi-supervised Batch Active Learning via Bilevel OptimizationCode1
Cold-start Active Learning through Self-supervised Language ModelingCode1
DEAL: Difficulty-aware Active Learning for Semantic SegmentationCode1
Active Domain Adaptation via Clustering Uncertainty-weighted EmbeddingsCode1
Deep Active Learning for Joint Classification & Segmentation with Weak AnnotatorCode1
SeqMix: Augmenting Active Sequence Labeling via Sequence MixupCode1
OLALA: Object-Level Active Learning for Efficient Document Layout AnnotationCode1
Neural BootstrapperCode1
HUMAN: Hierarchical Universal Modular ANnotatorCode1
Active Learning for Bayesian 3D Hand Pose EstimationCode1
Multi-task Causal Learning with Gaussian ProcessesCode1
Synbols: Probing Learning Algorithms with Synthetic DatasetsCode1
Bayesian Force Fields from Active Learning for Simulation of Inter-Dimensional Transformation of StaneneCode1
Deep Active Learning in Remote Sensing for data efficient Change DetectionCode1
Contextual Diversity for Active LearningCode1
DeepDrummer : Generating Drum Loops using Deep Learning and a Human in the LoopCode1
DEAL: Deep Evidential Active Learning for Image ClassificationCode1
On uncertainty estimation in active learning for image segmentationCode1
ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property PredictionCode1
Confidence-Aware Learning for Deep Neural NetworksCode1
CheXpert++: Approximating the CheXpert labeler for Speed,Differentiability, and Probabilistic OutputCode1
Graph Policy Network for Transferable Active Learning on GraphsCode1
Open Source Software for Efficient and Transparent ReviewsCode1
Output-Weighted Optimal Sampling for Bayesian Experimental Design and Uncertainty QuantificationCode1
Sequential Graph Convolutional Network for Active LearningCode1
Bayesian active learning for production, a systematic study and a reusable libraryCode1
Active Invariant Causal Prediction: Experiment Selection through StabilityCode1
Learning compositional models of robot skills for task and motion planningCode1
A2-LINK: Recognizing Disguised Faces via Active Learning and Adversarial Noise based Inter-Domain KnowledgeCode1
Machine learning methods to detect money laundering in the Bitcoin blockchain in the presence of label scarcityCode1
Active Imitation Learning with Noisy GuidanceCode1
Active Learning for Coreference Resolution using Discrete AnnotationCode1
Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation from a Blackbox ModelCode1
Model Assertions for Monitoring and Improving ML ModelsCode1
Deep Active Learning for Biased Datasets via Fisher Kernel Self-SupervisionCode1
Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral MeasuresCode1
Towards Robust and Reproducible Active Learning Using Neural NetworksCode1
Reinforced active learning for image segmentationCode1
LTP: A New Active Learning Strategy for CRF-Based Named Entity RecognitionCode1
A deep active learning system for species identification and counting in camera trap imagesCode1
Detecting Underspecification with Local EnsemblesCode1
A-LINK: Recognizing Disguised Faces via Active Learning based Inter-Domain KnowledgeCode1
Deep Active Learning for Axon-Myelin Segmentation on Histology DataCode1
Show:102550
← PrevPage 6 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