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 2726–2750 of 3569 papers

TitleStatusHype
Two-Step Meta-Learning for Time-Series Forecasting Ensemble—0
Hybrid Consistency Training with Prototype Adaptation for Few-Shot Learning—0
Finding the Homology of Decision Boundaries with Active LearningCode0
Automatic selection of clustering algorithms using supervised graph embeddingCode0
Dynamic backdoor attacks against federated learning—0
Towards Zero-Shot Learning with Fewer Seen Class Examples—0
Testing the Genomic Bottleneck Hypothesis in Hebbian Meta-LearningCode0
Convergence Properties of Stochastic Hypergradients—0
A Nested Bi-level Optimization Framework for Robust Few Shot Learning—0
FS-HGR: Few-shot Learning for Hand Gesture Recognition via ElectroMyography—0
Fast & Slow Learning: Incorporating Synthetic Gradients in Neural Memory Controllers—0
Know What You Don't Need: Single-Shot Meta-Pruning for Attention Heads—0
Confusable Learning for Large-class Few-Shot Classification—0
FDNAS: Improving Data Privacy and Model Diversity in AutoML—0
A Few Shot Adaptation of Visual Navigation Skills to New Observations using Meta-Learning—0
Transfer Meta-Learning: Information-Theoretic Bounds and Information Meta-Risk Minimization—0
Specialization in Hierarchical Learning Systems—0
Meta-Learning for Natural Language Understanding under Continual Learning FrameworkCode0
Meta-learning Transferable Representations with a Single Target Domain—0
Bilevel Continual Learning—0
Towards Low-Resource Semi-Supervised Dialogue Generation with Meta-Learning—0
Discriminative Adversarial Domain Generalization with Meta-learning based Cross-domain ValidationCode0
Few-Shot Multi-Hop Relation Reasoning over Knowledge Bases—0
Combining Domain-Specific Meta-Learners in the Parameter Space for Cross-Domain Few-Shot Classification—0
A Distribution-Dependent Analysis of Meta-Learning—0
Show:102550
← PrevPage 110 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