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 2251–2275 of 3073 papers

TitleStatusHype
Joint Active Learning with Feature Selection via CUR Matrix Decomposition—0
JointMap: Joint Query Intent Understanding For Modeling Intent Hierarchies in E-commerce Search—0
Joint Optimization of User-desired Content in Multi-document Summaries by Learning from User Feedback—0
Joint Out-of-Distribution Filtering and Data Discovery Active Learning—0
Judging the Quality of Automatically Generated Gap-fill Question using Active Learning—0
JuryGCN: Quantifying Jackknife Uncertainty on Graph Convolutional Networks—0
Just Label What You Need: Fine-Grained Active Selection for Perception and Prediction through Partially Labeled Scenes—0
Just Sort It! A Simple and Effective Approach to Active Preference Learning—0
KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection—0
Keeping Deep Lithography Simulators Updated: Global-Local Shape-Based Novelty Detection and Active Learning—0
K-nn active learning under local smoothness condition—0
K-NN active learning under local smoothness assumption—0
Knowledge Completion for Generics using Guided Tensor Factorization—0
Autonomous Wireless Systems with Artificial Intelligence—0
Knowledge Modelling and Active Learning in Manufacturing—0
Label Distribution Learning using the Squared Neural Family on the Probability Simplex—0
Label-Efficient Interactive Time-Series Anomaly Detection—0
Label-Efficient Point Cloud Semantic Segmentation: An Active Learning Approach—0
Label-efficient Single Photon Images Classification via Active Learning—0
LADA: Look-Ahead Data Acquisition via Augmentation for Active Learning—0
LAMBO: Large AI Model Empowered Edge Intelligence—0
Language Grounding through Social Interactions and Curiosity-Driven Multi-Goal Learning—0
Language Model-Driven Data Pruning Enables Efficient Active Learning—0
Language Model-Enhanced Message Passing for Heterophilic Graph Learning—0
Language Resource Addition: Dictionary or Corpus?—0
Show:102550
← PrevPage 91 of 123Next →

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