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 1671–1680 of 3569 papers

TitleStatusHype
FORML: A Riemannian Hessian-free Method for Meta-learning on Stiefel Manifolds—0
Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification—0
Double Meta-Learning for Data Efficient Policy Optimization in Non-Stationary Environments—0
Learning to Learn Group Alignment: A Self-Tuning Credo Framework with Multiagent Teams—0
Leveraging Auxiliary Task Relevance for Enhanced Bearing Fault Diagnosis through Curriculum Meta-learning—0
Leveraging Multi-Source Weak Social Supervision for Early Detection of Fake News—0
Constructing a meta-learner for unsupervised anomaly detection—0
Learning to Learn: Meta-Critic Networks for Sample Efficient Learning—0
Learning to Learn Morphological Inflection for Resource-Poor Languages—0
Forecast with Forecasts: Diversity Matters—0
Show:102550
← PrevPage 168 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