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 221–230 of 3569 papers

TitleStatusHype
Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-ExpertsCode1
Learning to Learn and Sample BRDFsCode1
Hypernetwork approach to Bayesian MAMLCode1
MetaPrompting: Learning to Learn Better PromptsCode1
Expanding the Deployment Envelope of Behavior Prediction via Adaptive Meta-LearningCode1
Learning Symbolic Model-Agnostic Loss Functions via Meta-LearningCode1
BOME! Bilevel Optimization Made Easy: A Simple First-Order ApproachCode1
Improving Fake News Detection of Influential Domain via Domain- and Instance-Level TransferCode1
Learning to Weight Samples for Dynamic Early-exiting NetworksCode1
MetaMask: Revisiting Dimensional Confounder for Self-Supervised LearningCode1
Show:102550
← PrevPage 23 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