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 2351–2400 of 3073 papers

TitleStatusHype
Regional based query in graph active learningCode0
Adapting Behaviour via Intrinsic Reward: A Survey and Empirical Study—0
BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active LearningCode0
Batch Active Learning Using Determinantal Point ProcessesCode0
A sparse annotation strategy based on attention-guided active learning for 3D medical image segmentation—0
RadGrad: Active learning with loss gradients—0
Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive ProcessesCode1
Deep Active Learning for Anchor User PredictionCode0
Low-resource Deep Entity Resolution with Transfer and Active Learning—0
Active Generative Adversarial Network for Image Classification—0
Bounded Expectation of Label Assignment: Dataset Annotation by Supervised Splitting with Bias-Reduction Techniques—0
Online Active Learning of Reject Option Classifiers—0
Non-Parametric Calibration for ClassificationCode0
Evaluation of Seed Set Selection Approaches and Active Learning Strategies in Predictive Coding—0
Human-Machine Collaboration for Fast Land Cover Mapping—0
Self-Supervised Exploration via DisagreementCode1
Deep Batch Active Learning by Diverse, Uncertain Gradient Lower BoundsCode1
Context-driven Active and Incremental Activity Recognition—0
Multi-modal Active Learning From Human Data: A Deep Reinforcement Learning Approach—0
Preference-based Interactive Multi-Document SummarisationCode0
Active Deep Decoding of Linear Codes—0
Diameter-based Interactive Structure Discovery—0
Reliable training and estimation of variance networksCode0
Bayesian Active Learning With Abstention Feedbacks—0
Data-efficient Neural Text Compression with Interactive LearningCode0
Practical, Efficient, and Customizable Active Learning for Named Entity Recognition in the Digital HumanitiesCode0
Active Learning for Binary Classification with Abstention—0
Minimum-Margin Active Learning—0
ActiveHARNet: Towards On-Device Deep Bayesian Active Learning for Human Activity RecognitionCode0
Understanding Goal-Oriented Active Learning via Influence Functions—0
Learning by Active Nonlinear Diffusion—0
The Label Complexity of Active Learning from Observational DataCode0
Training Data Subset Search with Ensemble Active Learning—0
MaxiMin Active Learning in Overparameterized Model Classes—0
Correlation Clustering with Adaptive Similarity QueriesCode0
Dual Active Sampling on Batch-Incremental Active LearningCode0
A framework for the extraction of Deep Neural Networks by leveraging public data—0
Constraining the Parameters of High-Dimensional Models with Active LearningCode0
Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active LearningCode0
Graph-based Semi-Supervised & Active Learning for Edge FlowsCode0
Collaborative Interactive Learning -- A clarification of terms and a differentiation from other research fields—0
Multi-fidelity classification using Gaussian processes: accelerating the prediction of large-scale computational modelsCode0
Learning Loss for Active LearningCode1
Reliable Uncertainty Estimates in Deep Neural Networks using Noise Contrastive Priors—0
Deep Ensemble Bayesian Active Learning : Adressing the Mode Collapse issue in Monte Carlo dropout via Ensembles—0
Bayesian Generative Active Deep Learning—0
Factored Contextual Policy Search with Bayesian Optimization—0
Informative sample generation using class aware generative adversarial networks for classification of chest Xrays—0
Disagreement-based Active Learning in Online Settings—0
ProductNet: a Collection of High-Quality Datasets for Product Representation Learning—0
Show:102550
← PrevPage 48 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