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 1101–1110 of 3569 papers

TitleStatusHype
Meta-Learning with Adaptive Weighted Loss for Imbalanced Cold-Start RecommendationCode0
MetaLDC: Meta Learning of Low-Dimensional Computing Classifiers for Fast On-Device Adaption—0
Bayes meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayes—0
Personalized Privacy-Preserving Framework for Cross-Silo Federated LearningCode0
MONGOOSE: Path-wise Smooth Bayesian Optimisation via Meta-learning—0
Mask-guided BERT for Few Shot Text Classification—0
Nystrom Method for Accurate and Scalable Implicit DifferentiationCode1
Incremental Few-Shot Object Detection via Simple Fine-Tuning ApproachCode1
CMVAE: Causal Meta VAE for Unsupervised Meta-LearningCode0
Deep Neural Networks based Meta-Learning for Network Intrusion Detection—0
Show:102550
← PrevPage 111 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