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 3351–3360 of 3569 papers

TitleStatusHype
Concurrent Meta Reinforcement LearningCode0
Learning How to Demodulate from Few Pilots via Meta-LearningCode0
Reproducing Meta-learning with differentiable closed-form solversCode0
Zero-Shot Task TransferCode0
NoRML: No-Reward Meta Learning—0
Provable Guarantees for Gradient-Based Meta-LearningCode0
Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation—0
Adversarial Attacks on Graph Neural Networks via Meta LearningCode0
Online Meta-Learning—0
Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-TimeCode0
Show:102550
← PrevPage 336 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