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 1521–1530 of 3569 papers

TitleStatusHype
ELF-UA: Efficient Label-Free User Adaptation in Gaze Estimation—0
Electrocardiogram-Language Model for Few-Shot Question Answering with Meta Learning—0
Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence—0
Electrical Load Forecasting over Multihop Smart Metering Networks with Federated Learning—0
Electrical Load Forecasting in Smart Grid: A Personalized Federated Learning Approach—0
Beyond Exponentially Discounted Sum: Automatic Learning of Return Function—0
A Meta-Learning Perspective on Cold-Start Recommendations for Items—0
Adaptive Reinforcement Learning through Evolving Self-Modifying Neural Networks—0
Elastically-Constrained Meta-Learner for Federated Learning—0
Efficient Unified Demosaicing for Bayer and Non-Bayer Patterned Image Sensors—0
Show:102550
← PrevPage 153 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