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 641–650 of 3569 papers

TitleStatusHype
Interactive singing melody extraction based on active adaptation—0
Distilling Symbolic Priors for Concept Learning into Neural Networks—0
Discovering Temporally-Aware Reinforcement Learning AlgorithmsCode1
Learning mirror maps in policy mirror descent—0
Progressive Conservative Adaptation for Evolving Target Domains—0
Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment—0
More Flexible PAC-Bayesian Meta-Learning by Learning Learning AlgorithmsCode0
Learning a Decision Tree Algorithm with TransformersCode2
Is Mamba Capable of In-Context Learning?Code1
Automatic Combination of Sample Selection Strategies for Few-Shot Learning—0
Show:102550
← PrevPage 65 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