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 3021–3030 of 3569 papers

TitleStatusHype
The Sample Complexity of Meta Sparse Regression—0
Few-shot acoustic event detection via meta-learning—0
Meta-learning for mixed linear regression—0
Structured Prediction for Conditional Meta-LearningCode0
Personalized Federated Learning: A Meta-Learning Approach—0
Meta Segmentation Network for Ultra-Resolution Medical Images—0
Curriculum in Gradient-Based Meta-Reinforcement Learning—0
Few-Shot Few-Shot Learning and the role of Spatial Attention—0
Theoretical Convergence of Multi-Step Model-Agnostic Meta-LearningCode0
Differentiable Bandit Exploration—0
Show:102550
← PrevPage 303 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