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 2341–2350 of 3569 papers

TitleStatusHype
MCML: A Novel Memory-based Contrastive Meta-Learning Method for Few Shot Slot Tagging—0
Probing Pre-trained Auto-regressive Language Models for Named Entity Typing and RecognitionCode0
Adaptation-Agnostic Meta-TrainingCode0
CMML: Contextual Modulation Meta Learning for Cold-Start RecommendationCode0
Efficient Gaussian Neural Processes for Regression—0
Fairness-Aware Online Meta-learning—0
Self-Supervised Video Representation Learning with Meta-Contrastive Network—0
Learning-to-learn non-convex piecewise-Lipschitz functions—0
Scarce Data Driven Deep Learning of Drones via Generalized Data Distribution Space—0
Is Nash Equilibrium Approximator Learnable?—0
Show:102550
← PrevPage 235 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