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 1301–1310 of 3569 papers

TitleStatusHype
Meta-learning Based Short-Term Passenger Flow Prediction for Newly-Operated Urban Rail Transit Stations—0
Multi-Task Meta Learning: learn how to adapt to unseen tasksCode0
Few-Shot Visual Question Generation: A Novel Task and Benchmark Datasets—0
Few-shot Relational Reasoning via Connection Subgraph PretrainingCode1
Improving the Reliability for Confidence Estimation—0
Evaluated CMI Bounds for Meta Learning: Tightness and Expressiveness—0
A Unified Framework with Meta-dropout for Few-shot Learning—0
The Devil is in the Details: On Models and Training Regimes for Few-Shot Intent Classification—0
Stock Trading Volume Prediction with Dual-Process Meta-LearningCode1
Meta-Learning with Self-Improving Momentum TargetCode1
Show:102550
← PrevPage 131 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