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 3201–3210 of 3569 papers

TitleStatusHype
Robust Few-shot Learning Without Using any Adversarial SamplesCode0
Noise-Aware Differentially Private Regression via Meta-LearningCode0
Unsupervised Meta-Learning via Dynamic Head and Heterogeneous Task Construction for Few-Shot ClassificationCode0
Noisy Zero-Shot Coordination: Breaking The Common Knowledge Assumption In Zero-Shot Coordination GamesCode0
Domain Generalization via Semi-supervised Meta LearningCode0
Domain Adaptive Dialog Generation via Meta LearningCode0
Meta-Learning Bidirectional Update RulesCode0
How Low Can We Go: Trading Memory for Error in Low-Precision TrainingCode0
Robust LLM Unlearning with MUDMAN: Meta-Unlearning with Disruption Masking And NormalizationCode0
Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes TheoryCode0
Show:102550
← PrevPage 321 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