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 3081–3090 of 3569 papers

TitleStatusHype
MetaCI: Meta-Learning for Causal Inference in a Heterogeneous Population—0
Improved Few-Shot Visual Classification—0
MetaFun: Meta-Learning with Iterative Functional UpdatesCode0
MetalGAN: Multi-Domain Label-Less Image Synthesis Using cGANs and Meta-Learning—0
Learning to Recommend via Meta Parameter Partition—0
BADGER: Learning to (Learn [Learning Algorithms] through Multi-Agent Communication)Code0
MetaInit: Initializing learning by learning to initialize—0
Efficient Meta Learning via Minibatch Proximal Update—0
Learning to Learn By Self-CritiqueCode0
MetAdapt: Meta-Learned Task-Adaptive Architecture for Few-Shot Classification—0
Show:102550
← PrevPage 309 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