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 2521–2530 of 3569 papers

TitleStatusHype
Causality-Driven One-Shot Learning for Prostate Cancer Grading from MRI—0
CAZSL: Zero-Shot Regression for Pushing Models by Generalizing Through Context—0
CCML: Curriculum and Contrastive Learning Enhanced Meta-Learner for Personalized Spatial Trajectory Prediction—0
CDRNP: Cross-Domain Recommendation to Cold-Start Users via Neural Process—0
Cellular neuromodulation in artificial networks—0
Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation Extraction—0
Challenge Closed-book Science Exam: A Meta-learning Based Question Answering System—0
Challenges and Opportunities for Machine Learning Classification of Behavior and Mental State from Images—0
Characterizing Policy Divergence for Personalized Meta-Reinforcement Learning—0
CHOMET: Conditional Handovers via Meta-Learning—0
Show:102550
← PrevPage 253 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