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 2921–2930 of 3569 papers

TitleStatusHype
Provably Efficient Model-based Policy Adaptation—0
Meta-Learning for Recalibration of EMG-Based Upper Limb Prostheses—0
Learning-to-Learn Personalised Human Activity Recognition Models—0
BI-MAML: Balanced Incremental Approach for Meta Learning—0
Backdoor Attacks on Federated Meta-Learning—0
Meta-Learning GNN Initializations for Low-Resource Molecular Property Prediction—0
Attentive Feature Reuse for Multi Task Meta learning—0
Task-similarity Aware Meta-learning through Nonparametric Kernel Regression—0
Taming the Herd: Multi-Modal Meta-Learning with a Population of Agents—0
Learning to Learn Kernels with Variational Random FeaturesCode0
Show:102550
← PrevPage 293 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