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 2901–2925 of 3569 papers

TitleStatusHype
Uniform Priors for Data-Efficient Transfer—0
Robustifying Sequential Neural Processes—0
Set Based Stochastic Subsampling—0
On the Global Optimality of Model-Agnostic Meta-Learning—0
Meta Learning for Support Recovery in High-dimensional Precision Matrix Estimation—0
Don’t Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights—0
Don't Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights—0
Learning to Generate Noise for Multi-Attack RobustnessCode0
Siamese Meta-Learning and Algorithm Selection with 'Algorithm-Performance Personas' [Proposal]—0
Gradient-EM Bayesian Meta-learning—0
Meta Learning in the Continuous Time Limit—0
Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models—0
Robust Meta-learning for Mixed Linear Regression with Small Batches—0
Enhancing Few-Shot Image Classification with Unlabelled Examples—0
META-Learning Eligibility Traces for More Sample Efficient Temporal Difference LearningCode0
Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters—0
Learning to Learn with Feedback and Local Plasticity—0
Automatic Validation of Textual Attribute Values in E-commerce Catalog by Learning with Limited Labeled Data—0
Towards an Unsupervised Method for Model Selection in Few-Shot Learning—0
Physics-aware Spatiotemporal Modules with Auxiliary Tasks for Meta-Learning—0
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
Show:102550
← PrevPage 117 of 143Next →
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