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 3161–3170 of 3569 papers

TitleStatusHype
Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph CompletionCode0
Localized Generations with Deep Neural Networks for Multi-Scale Structured Datasets—0
Decoder Choice Network for Meta-LearningCode0
Semi-Supervised Few-Shot Learning with a Controlled Degree of Task-Adaptive Conditioning—0
Decoupling Adaptation from Modeling with Meta-Optimizers for Meta Learning—0
Role of two learning rates in convergence of model-agnostic meta-learning—0
NORML: Nodal Optimization for Recurrent Meta-Learning—0
Meta-Learning for Variational Inference—0
ES-MAML: Simple Hessian-Free Meta LearningCode0
A Data-Efficient Mutual Information Neural Estimator for Statistical Dependency Testing—0
Show:102550
← PrevPage 317 of 357Next →
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