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 3401–3410 of 3569 papers

TitleStatusHype
Dataset2Vec: Learning Dataset Meta-FeaturesCode0
AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel LearningCode0
Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial AttacksCode0
PABBO: Preferential Amortized Black-Box OptimizationCode0
Generalizing Reward Modeling for Out-of-Distribution Preference LearningCode0
PAC-Bayes Bounds for Meta-learning with Data-Dependent PriorCode0
AutonoML: Towards an Integrated Framework for Autonomous Machine LearningCode0
Understanding Prompt Tuning and In-Context Learning via Meta-LearningCode0
Generalized Face Anti-spoofing via Finer Domain Partition and Disentangling Liveness-irrelevant FactorsCode0
Generalization Bounds For Meta-Learning: An Information-Theoretic AnalysisCode0
Show:102550
← PrevPage 341 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