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 1861–1870 of 3569 papers

TitleStatusHype
Few-Shot Named Entity Recognition: An Empirical Baseline Study—0
MetaTS: Meta Teacher-Student Network for Multilingual Sequence Labeling with Minimal Supervision—0
Beyond Reptile: Meta-Learned Dot-Product Maximization between Gradients for Improved Single-Task Regularization—0
End-to-End Learning of Deep Kernel Acquisition Functions for Bayesian Optimization—0
Influential Prototypical Networks for Few Shot Learning: A Dermatological Case Study—0
RF-Net: a Unified Meta-learning Framework for RF-enabled One-shot Human Activity RecognitionCode1
A Scalable AutoML Approach Based on Graph Neural NetworksCode0
Domain Agnostic Few-Shot Learning For Document Intelligence—0
Click-Based Student Performance Prediction: A Clustering Guided Meta-Learning Approach—0
Learning where to learn: Gradient sparsity in meta and continual learningCode1
Show:102550
← PrevPage 187 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