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 2311–2320 of 3569 papers

TitleStatusHype
Automatic Forecasting via Meta-Learning—0
Neural Variational Dropout Processes—0
Improved Generalization Risk Bounds for Meta-Learning with PAC-Bayes-kl Analysis—0
3D Meta-Registration: Meta-learning 3D Point Cloud Registration Functions—0
Generalization Bounds For Meta-Learning: An Information-Theoretic AnalysisCode0
Learning to Adapt to Semantic Shift—0
Do What Nature Did To Us: Evolving Plastic Recurrent Neural Networks For Generalized Tasks—0
Multimodality in Meta-Learning: A Comprehensive Survey—0
ST-MAML: A Stochastic-Task based Method for Task-Heterogeneous Meta-Learning—0
Learning to Selectively Learn for Weakly-supervised Paraphrase Generation—0
Show:102550
← PrevPage 232 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