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

Showing 21762200 of 3073 papers

TitleStatusHype
Streaming Active Deep Forest for Evolving Data Stream Classification0
Stealing Black-Box Functionality Using The Deep Neural Tree ArchitectureCode0
Adaptive Region-Based Active Learning0
Information Condensing Active LearningCode0
Let Me At Least Learn What You Really Like: Dealing With Noisy Humans When Learning Preferences0
On State Variables, Bandit Problems and POMDPs0
Learning switched systems from simulation models0
Active Learning for Sound Event Detection0
Efficient active learning of sparse halfspaces with arbitrary bounded noise0
Task-Aware Variational Adversarial Active Learning0
Outlier Guided Optimization of Abdominal Segmentation0
Hierarchical Gaussian Process Priors for Bayesian Neural Network Weights0
ACTIVETHIEF: Model Extraction Using Active Learning and Unannotated Public DataCode0
Ready Policy One: World Building Through Active Learning0
Value of Information Analysis via Active Learning and Knowledge Sharing in Error-Controlled Adaptive Kriging0
Context Aware Image Annotation in Active Learning0
Rényi Entropy Bounds on the Active Learning Cost-Performance Tradeoff0
ALPINE: Active Link Prediction using Network Embedding0
Boosting API Recommendation with Implicit Feedback0
Active Learning for Identification of Linear Dynamical Systems0
Binary Classification with XOR Queries: Fundamental Limits and An Efficient Algorithm0
A Graph-Based Approach for Active Learning in Regression0
Fase-AL -- Adaptation of Fast Adaptive Stacking of Ensembles for Supporting Active Learning0
Scale bridging materials physics: Active learning workflows and integrable deep neural networks for free energy function representations in alloys0
QActor: On-line Active Learning for Noisy Labeled Stream Data0
Show:102550
← PrevPage 88 of 123Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TypiClustAccuracy93.2Unverified
2PT4ALAccuracy93.1Unverified
3Learning lossAccuracy91.01Unverified
4CoreGCNAccuracy90.7Unverified
5Core-setAccuracy89.92Unverified
6Random Baseline (Resnet18)Accuracy88.45Unverified
7Random Baseline (VGG16)Accuracy85.09Unverified