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 1301–1350 of 3073 papers

TitleStatusHype
Consistent Training via Energy-Based GFlowNets for Modeling Discrete Joint Distributions—0
Learning to Detect Interesting Anomalies—0
Radically Lower Data-Labeling Costs for Visually Rich Document Extraction Models—0
Poisson Reweighted Laplacian Uncertainty Sampling for Graph-based Active LearningCode0
Trust and Believe -- Should We? Evaluating the Trustworthiness of Twitter Users—0
COMET-QE and Active Learning for Low-Resource Machine Translation—0
Eeny, meeny, miny, moe. How to choose data for morphological inflectionCode0
Active Learning Framework to Automate NetworkTraffic Classification—0
Uncertainty Sentence Sampling by Virtual Adversarial Perturbation—0
From colouring-in to pointillism: revisiting semantic segmentation supervision—0
Worst-Case Adaptive Submodular Cover—0
Active Learning for Single Neuron Models with Lipschitz Non-Linearities—0
Batch Multi-Fidelity Active Learning with Budget Constraints—0
Learning General World Models in a Handful of Reward-Free Deployments—0
Active Learning of Discrete-Time Dynamics for Uncertainty-Aware Model Predictive Control—0
Targeted active learning for probabilistic modelsCode0
Uncertainty Disentanglement with Non-stationary Heteroscedastic Gaussian Processes for Active Learning—0
Active Learning for Imbalanced Civil Infrastructure Data—0
Learning Preferences for Interactive AutonomyCode0
A Survey of Active Learning for Natural Language Processing—0
Virtual Reality via Object Pose Estimation and Active Learning: Realizing Telepresence Robots with Aerial Manipulation Capabilities—0
ISEE.U: Distributed online active target localization with unpredictable targets—0
Semantic Segmentation with Active Semi-Supervised Representation Learning—0
GFlowCausal: Generative Flow Networks for Causal DiscoveryCode0
Active Learning with Neural Networks: Insights from Nonparametric Statistics—0
Improving the Intra-class Long-tail in 3D Detection via Rare Example Mining—0
Geometric Active Learning for Segmentation of Large 3D Volumes—0
Reducing Annotation Effort by Identifying and Labeling Contextually Diverse Classes for Semantic Segmentation Under Domain ShiftCode0
TiDAL: Learning Training Dynamics for Active LearningCode0
Data augmentation on-the-fly and active learning in data stream classificationCode0
JuryGCN: Quantifying Jackknife Uncertainty on Graph Convolutional Networks—0
Deep Active Ensemble Sampling For Image Classification—0
The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes—0
Few-Shot Continual Active Learning by a Robot—0
PropertyDAG: Multi-objective Bayesian optimization of partially ordered, mixed-variable properties for biological sequence design—0
Is margin all you need? An extensive empirical study of active learning on tabular data—0
To Softmax, or not to Softmax: that is the question when applying Active Learning for Transformer ModelsCode0
An Active Learning Reliability Method for Systems with Partially Defined Performance FunctionsCode0
DIAGNOSE: Avoiding Out-of-distribution Data using Submodular Information Measures—0
Active Learning for Regression with Aggregated Outputs—0
CLINICAL: Targeted Active Learning for Imbalanced Medical Image Classification—0
Nonstationary data stream classification with online active learning and siamese neural networksCode0
Robust Active Distillation—0
Improved Algorithms for Neural Active LearningCode0
Detecting Minority Arguments for Mutual Understanding: A Moderation Tool for the Online Climate Change DebateCode0
Improving Generative Flow Networks with Path Regularization—0
Active Transfer Prototypical Network: An Efficient Labeling Algorithm for Time-Series Data—0
Active Few-Shot Classification: a New Paradigm for Data-Scarce Learning Settings—0
From Weakly Supervised Learning to Active Learning—0
Smart Active Sampling to enhance Quality Assurance Efficiency—0
Show:102550
← PrevPage 27 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