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 2151–2200 of 3073 papers

TitleStatusHype
Deep Active Learning for Biased Datasets via Fisher Kernel Self-SupervisionCode1
Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral MeasuresCode1
Streaming Active Deep Forest for Evolving Data Stream Classification—0
Stealing Black-Box Functionality Using The Deep Neural Tree ArchitectureCode0
Towards Robust and Reproducible Active Learning Using Neural NetworksCode1
Information Condensing Active LearningCode0
Adaptive Region-Based Active Learning—0
Reinforced active learning for image segmentationCode1
Let Me At Least Learn What You Really Like: Dealing With Noisy Humans When Learning Preferences—0
On State Variables, Bandit Problems and POMDPs—0
Learning switched systems from simulation models—0
Active Learning for Sound Event Detection—0
Efficient active learning of sparse halfspaces with arbitrary bounded noise—0
Task-Aware Variational Adversarial Active Learning—0
Hierarchical Gaussian Process Priors for Bayesian Neural Network Weights—0
Outlier Guided Optimization of Abdominal Segmentation—0
ACTIVETHIEF: Model Extraction Using Active Learning and Unannotated Public DataCode0
Ready Policy One: World Building Through Active Learning—0
Context Aware Image Annotation in Active Learning—0
Value of Information Analysis via Active Learning and Knowledge Sharing in Error-Controlled Adaptive Kriging—0
Rényi Entropy Bounds on the Active Learning Cost-Performance Tradeoff—0
ALPINE: Active Link Prediction using Network Embedding—0
Boosting API Recommendation with Implicit Feedback—0
Active Learning for Identification of Linear Dynamical Systems—0
Binary Classification with XOR Queries: Fundamental Limits and An Efficient Algorithm—0
Scale bridging materials physics: Active learning workflows and integrable deep neural networks for free energy function representations in alloys—0
A Graph-Based Approach for Active Learning in Regression—0
Fase-AL -- Adaptation of Fast Adaptive Stacking of Ensembles for Supporting Active Learning—0
QActor: On-line Active Learning for Noisy Labeled Stream Data—0
Discovery of Self-Assembling π-Conjugated Peptides by Active Learning-Directed Coarse-Grained Molecular SimulationCode0
Learning Non-Markovian Reward Models in MDPs—0
Explainable Active Learning (XAL): An Empirical Study of How Local Explanations Impact Annotator Experience—0
Active Learning for Entity AlignmentCode0
Combining Federated and Active Learning for Communication-efficient Distributed Failure Prediction in Aeronautics—0
Early Forecasting of Text Classification Accuracy and F-Measure with Active Learning—0
Active and Incremental Learning with Weak Supervision—0
Projection based Active Gaussian Process Regression for Pareto Front Modeling—0
Active Learning over DNN: Automated Engineering Design Optimization for Fluid Dynamics Based on Self-Simulated Dataset—0
K-NN active learning under local smoothness assumption—0
Machine learning and AI-based approaches for bioactive ligand discovery and GPCR-ligand recognition—0
Noise-tolerant, Reliable Active Classification with Comparison Queries—0
Payoff Information and Learning in Signaling Games—0
Unsupervised Pool-Based Active Learning for Linear RegressionCode0
Adversarial vs behavioural-based defensive AI with joint, continual and active learning: automated evaluation of robustness to deception, poisoning and concept drift—0
What is the Value of Data? On Mathematical Methods for Data Quality Estimation—0
Domain-independent Extraction of Scientific Concepts from Research ArticlesCode0
LTP: A New Active Learning Strategy for CRF-Based Named Entity RecognitionCode1
Fair Active LearningCode0
Teach Me What You Want to Play: Learning Variants of Connect Four through Human-Robot Interaction—0
Learning the Valuations of a k-demand Agent—0
Show:102550
← PrevPage 44 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