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 621–630 of 3569 papers

TitleStatusHype
AReLU: Attention-based Rectified Linear UnitCode1
Learning To Learn and Remember Super Long Multi-Domain Task SequenceCode1
Hardware-adaptive Efficient Latency Prediction for NAS via Meta-LearningCode1
Learning to learn with quantum neural networks via classical neural networksCode1
Learning to Purify Noisy Labels via Meta Soft Label CorrectorCode1
Contrastive Meta-Learning for Partially Observable Few-Shot LearningCode1
Contrastive Meta Learning with Behavior Multiplicity for RecommendationCode1
Towards Task Sampler Learning for Meta-LearningCode1
ContrastNet: A Contrastive Learning Framework for Few-Shot Text ClassificationCode1
Look-ahead Meta Learning for Continual LearningCode1
Show:102550
← PrevPage 63 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