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 1676–1700 of 3073 papers

TitleStatusHype
WHAT TO DO IF SPARSE REPRESENTATION LEARNING FAILS UNEXPECTEDLY?—0
On Locality in Graph Learning via Graph Neural Network—0
Limitations of Active Learning With Deep Transformer Language Models—0
Sample Complexity of Deep Active Learning—0
Low-Budget Active Learning via Wasserstein Distance: An Integer Programming Approach—0
Pretrained models are active learners—0
Coherence-based Label Propagation over Time Series for Accelerated Active Learning—0
Vibration-based Uncertainty Estimation for Learning from Limited Supervision—0
What to Prioritize? Natural Language Processing for the Development of a Modern Bug Tracking Solution in Hardware Development—0
Active Learning for Argument Mining: A Practical Approach—0
Improving Question Answering Performance Using Knowledge Distillation and Active LearningCode0
Data Summarization via Bilevel Optimization—0
Bayesian Active Learning for Sim-to-Real Robotic Perception—0
A Survey on Cost Types, Interaction Schemes, and Annotator Performance Models in Selection Algorithms for Active Learning in Classification—0
Active Learning for Argument Strength EstimationCode0
Exploring Adversarial Examples for Efficient Active Learning in Machine Learning Classifiers—0
Fast and Sample-Efficient Interatomic Neural Network Potentials for Molecules and Materials Based on Gaussian MomentsCode0
Towards Overcoming Practical Obstacles to Deploying Deep Active Learning—0
MOFSimplify: Machine Learning Models with Extracted Stability Data of Three Thousand Metal-Organic Frameworks—0
FOMO: Topics versus documents in legal eDiscovery—0
Mitigating Sampling Bias and Improving Robustness in Active Learning—0
Robust Contrastive Active Learning with Feature-guided Query Strategies—0
Adaptive network reliability analysis: Methodology and applications to power grid—0
Active learning for reducing labeling effort in text classification tasksCode0
Open-World Active Learning with Stacking Ensemble for Self-Driving Cars—0
Show:102550
← PrevPage 68 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