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 1701–1725 of 3073 papers

TitleStatusHype
Perfect density models cannot guarantee anomaly detection—0
Performance-Guided LLM Knowledge Distillation for Efficient Text Classification at Scale—0
Personalized Image Aesthetics—0
Personalized Semi-Supervised Federated Learning for Human Activity Recognition—0
Personalized Text Retrieval for Learners of Chinese as a Foreign Language—0
Personalizing Gesture Recognition Using Hierarchical Bayesian Neural Networks—0
Perturbation-based Active Learning for Question Answering—0
Perturbation-based Graph Active Learning for Weakly-Supervised Belief Representation Learning—0
Perturbation-Based Two-Stage Multi-Domain Active Learning—0
Phase discovery with active learning: Application to structural phase transitions in equiatomic NiTi—0
Photonic architecture for reinforcement learning—0
Phrase-level Active Learning for Neural Machine Translation—0
Physics-constrained Active Learning for Soil Moisture Estimation and Optimal Sensor Placement—0
Physics-Coupled Spatio-Temporal Active Learning for Dynamical Systems—0
Physics-enhanced deep surrogates for partial differential equations—0
Physics-Informed CoKriging: A Gaussian-Process-Regression-Based Multifidelity Method for Data-Model Convergence—0
Physics-informed EDFA Gain Model Based on Active Learning—0
Physics-Informed Gaussian Process Classification for Constraint-Aware Alloy Design—0
Physics-Information-Aided Kriging: Constructing Covariance Functions using Stochastic Simulation Models—0
Picking groups instead of samples: A close look at Static Pool-based Meta-Active Learning—0
PI-CoF: A Bilevel Optimization Framework for Solving Active Learning Problems using Physics-Information—0
Pixel is All You Need: Adversarial Trajectory-Ensemble Active Learning for Salient Object Detection—0
Plex: Towards Reliability using Pretrained Large Model Extensions—0
Point Location and Active Learning: Learning Halfspaces Almost Optimally—0
Pool-Based Active Learning with Proper Topological Regions—0
Show:102550
← PrevPage 69 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