SOTAVerified

Meta-Learning

Meta-learning is a methodology considered with "learning to learn" machine learning algorithms.

( Image credit: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2751–2800 of 3569 papers

TitleStatusHype
MetaConcept: Learn to Abstract via Concept Graph for Weakly-Supervised Few-Shot Learning—0
Neural Interactive Collaborative FilteringCode1
Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen DomainsCode1
Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural ProcessesCode1
On the Outsized Importance of Learning Rates in Local Update MethodsCode0
End-to-End Simultaneous Translation System for IWSLT2020 Using Modality Agnostic Meta-Learning—0
End-to-End Offline Speech Translation System for IWSLT 2020 using Modality Agnostic Meta-Learning—0
Meta-Reinforced Multi-Domain State Generator for Dialogue Systems—0
Learning Low-Resource End-To-End Goal-Oriented Dialog for Fast and Reliable System Deployment—0
Multi-source Meta Transfer for Low Resource Multiple-Choice Question Answering—0
Hypernymy Detection for Low-Resource Languages via Meta Learning—0
Uniform Priors for Data-Efficient Transfer—0
Few-Shot Microscopy Image Cell SegmentationCode1
Universal linguistic inductive biases via meta-learningCode1
Laplacian Regularized Few-Shot LearningCode1
Robustifying Sequential Neural Processes—0
On the Iteration Complexity of Hypergradient ComputationCode1
Laplacian Regularized Few-Shot LearningCode1
Many-Class Few-Shot Learning on Multi-Granularity Class HierarchyCode1
Global Convergence and Generalization Bound of Gradient-Based Meta-Learning with Deep Neural NetsCode2
A Simple Approach to Case-Based Reasoning in Knowledge BasesCode1
Set Based Stochastic Subsampling—0
AReLU: Attention-based Rectified Linear UnitCode1
On the Global Optimality of Model-Agnostic Meta-Learning—0
Graph Prototypical Networks for Few-shot Learning on Attributed NetworksCode1
Don’t Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights—0
Meta Learning for Support Recovery in High-dimensional Precision Matrix Estimation—0
Learning with AMIGo: Adversarially Motivated Intrinsic GoalsCode1
Don't Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights—0
Learning to Generate Noise for Multi-Attack RobustnessCode0
Siamese Meta-Learning and Algorithm Selection with 'Algorithm-Performance Personas' [Proposal]—0
Gradient-EM Bayesian Meta-learning—0
Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian ProcessesCode1
Self-Supervised Prototypical Transfer Learning for Few-Shot ClassificationCode1
Meta Learning in the Continuous Time Limit—0
Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models—0
Enhancing Few-Shot Image Classification with Unlabelled Examples—0
MetaSDF: Meta-learning Signed Distance FunctionsCode1
Robust Meta-learning for Mixed Linear Regression with Small Batches—0
Self-supervised Knowledge Distillation for Few-shot LearningCode1
Learning to Learn with Feedback and Local Plasticity—0
Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters—0
Personalized Federated Learning with Moreau EnvelopesCode1
META-Learning Eligibility Traces for More Sample Efficient Temporal Difference LearningCode0
Towards an Unsupervised Method for Model Selection in Few-Shot Learning—0
Automatic Validation of Textual Attribute Values in E-commerce Catalog by Learning with Limited Labeled Data—0
Physics-aware Spatiotemporal Modules with Auxiliary Tasks for Meta-Learning—0
Flexible Dataset Distillation: Learn Labels Instead of ImagesCode1
Graph Meta Learning via Local SubgraphsCode1
Provably Efficient Model-based Policy Adaptation—0
Show:102550
← PrevPage 56 of 72Next →
All datasetsML10MT50ML45OMNIGLOT - 1-Shot, 20-way

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-train success rate97.8—Unverified
2MZMeta-train success rate97.6—Unverified
3MAMLMeta-test success rate36—Unverified
4RL^2Meta-test success rate10—Unverified
5DnCMeta-test success rate5.4—Unverified
6PEARLMeta-test success rate0—Unverified
#ModelMetricClaimedVerifiedStatus
1SoftModuleAverage Success Rate60—Unverified
2Multi-task multi-head SACAverage Success Rate35.85—Unverified
3DisCorAverage Success Rate26—Unverified
4NDPAverage Success Rate11—Unverified
#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-test success rate (zero-shot)18.5—Unverified
2MZMeta-test success rate (zero-shot)17.7—Unverified
#ModelMetricClaimedVerifiedStatus
1Metadrop% Test Accuracy95.75—Unverified