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 2541–2550 of 3569 papers

TitleStatusHype
Uncertainty-guided Model Generalization to Unseen Domains—0
Population-Based Evolution Optimizes a Meta-Learning Objective—0
Model-Agnostic Meta-Learning for EEG Motor Imagery Decoding in Brain-Computer-Interfacing—0
u-cf2vec: Representation Learning for Personalized Algorithm Selection in Recommender Systems—0
Scalable Online Recurrent Learning Using Columnar Neural NetworksCode0
Meta-Learning with MAML on Trees—0
Convergence and Accuracy Trade-Offs in Federated Learning and Meta-Learning—0
Learning to Continually Learn Rapidly from Few and Noisy DataCode0
Structure-Enhanced Meta-Learning For Few-Shot Graph ClassificationCode0
Meta Learning Black-Box Population-Based Optimizers—0
Show:102550
← PrevPage 255 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