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 2826–2850 of 3569 papers

TitleStatusHype
MetaMIML: Meta Multi-Instance Multi-Label Learning—0
Meta Mirror Descent: Optimiser Learning for Fast Convergence—0
MetaMix: Improved Meta-Learning with Interpolation-based Consistency Regularization—0
MetaMix: Towards Corruption-Robust Continual Learning With Temporally Self-Adaptive Data Transformation—0
MetaMixUp: Learning Adaptive Interpolation Policy of MixUp with Meta-Learning—0
Meta-Model-Based Meta-Policy Optimization—0
MetaMolGen: A Neural Graph Motif Generation Model for De Novo Molecular Design—0
Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning—0
MetaNeRV: Meta Neural Representations for Videos with Spatial-Temporal Guidance—0
Meta Neural Coordination—0
Adaptive Asynchronous Control Using Meta-learned Neural Ordinary Differential Equations—0
MetaNO: How to Transfer Your Knowledge on Learning Hidden Physics—0
Bayesian Active Meta-Learning for Few Pilot Demodulation and EqualizationCode0
Learning to Learn Single Domain GeneralizationCode0
Learning to Learn Transferable AttackCode0
MetaSD: A Unified Framework for Scalable Downscaling of Meteorological Variables in Diverse SituationsCode0
Fast Finite Width Neural Tangent KernelCode0
Learning to Learn Variational Semantic MemoryCode0
Context-Aware Adapter Tuning for Few-Shot Relation Learning in Knowledge GraphsCode0
Constructing Multiple Tasks for Augmentation: Improving Neural Image Classification With K-means FeaturesCode0
Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category GraphCode0
Few-Shot Learning with Localization in Realistic SettingsCode0
Learning to Learn Kernels with Variational Random FeaturesCode0
Learning to Learn from Noisy Labeled DataCode0
META-Learning State-based Eligibility Traces for More Sample-Efficient Policy EvaluationCode0
Show:102550
← PrevPage 114 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