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 261–270 of 3569 papers

TitleStatusHype
Learning to Adapt to Low-Resource Paraphrase Generation—0
A Meta-Learning Approach to Bayesian Causal DiscoveryCode0
MetaRuleGPT: Recursive Numerical Reasoning of Language Models Trained with Simple Rules—0
Spatio-Temporal Fuzzy-oriented Multi-Modal Meta-Learning for Fine-grained Emotion RecognitionCode0
Consistency of Compositional Generalization across Multiple LevelsCode0
TSEML: A task-specific embedding-based method for few-shot classification of cancer molecular subtypesCode0
Learning from Noisy Labels via Self-Taught On-the-Fly Meta Loss Rescaling—0
Reservoir Computing for Fast, Simplified Reinforcement Learning on Memory Tasks—0
Generalizable Representation Learning for fMRI-based Neurological Disorder IdentificationCode0
Memory-Reduced Meta-Learning with Guaranteed Convergence—0
Show:102550
← PrevPage 27 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