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 541–550 of 3569 papers

TitleStatusHype
Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link PredictionCode1
Personalized Image Aesthetics Assessment via Meta-Learning With Bilevel Gradient OptimizationCode1
MC-BERT: Efficient Language Pre-Training via a Meta ControllerCode1
Learning to Stop While Learning to PredictCode1
Adaptive Subspaces for Few-Shot LearningCode1
Attentive Weights Generation for Few Shot Learning via Information MaximizationCode1
Training Noise-Robust Deep Neural Networks via Meta-LearningCode1
How to Retrain Recommender System? A Sequential Meta-Learning MethodCode1
Few-Shot Open-Set Recognition using Meta-LearningCode1
An Analysis of the Adaptation Speed of Causal ModelsCode1
Show:102550
← PrevPage 55 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