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 2351–2375 of 3569 papers

TitleStatusHype
Reproducibility Report: La-MAML: Look-ahead Meta Learning for Continual LearningCode0
Meta-Thompson Sampling—0
Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural networkCode1
Nonstochastic Bandits with Infinitely Many Experts—0
Meta-Learning for Koopman Spectral Analysis with Short Time-series—0
A Single-Timescale Method for Stochastic Bilevel Optimization—0
Meta Discovery: Learning to Discover Novel Classes given Very Limited DataCode1
MetaTune: Meta-Learning Based Cost Model for Fast and Efficient Auto-tuning Frameworks—0
Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning—0
Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Tasks—0
PAC-Bayes Bounds for Meta-learning with Data-Dependent PriorCode0
Meta-Learning with Neural Tangent Kernels—0
Federated Reconstruction: Partially Local Federated LearningCode1
In-Loop Meta-Learning with Gradient-Alignment Reward—0
Meta-strategy for Learning Tuning Parameters with Guarantees—0
Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agentsCode1
Meta-learning with negative learning rates—0
Meta ordinal weighting net for improving lung nodule classification—0
On Data Efficiency of Meta-learning—0
Meta-Reinforcement Learning for Reliable Communication in THz/VLC Wireless VR NetworksCode0
Few-Shot Domain Adaptation for Grammatical Error Correction via Meta-Learning—0
Few-Shot Learning for Road Object Detection—0
CORL: Compositional Representation Learning for Few-Shot Classification—0
Generalising via Meta-Examples for Continual Learning in the WildCode1
ProtoDA: Efficient Transfer Learning for Few-Shot Intent Classification—0
Show:102550
← PrevPage 95 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