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 2701–2725 of 3569 papers

TitleStatusHype
Unsupervised Alternating Optimization for Blind Hyperspectral Imagery Super-resolution—0
SB-MTL: Score-based Meta Transfer-Learning for Cross-Domain Few-Shot Learning—0
Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains—0
Margin-Based Transfer Bounds for Meta Learning with Deep Feature Embedding—0
A meta-learning approach to (re)discover plasticity rules that carve a desired function into a neural network—0
Meta-learning from Tasks with Heterogeneous Attribute SpacesCode0
Differentiable Meta-Learning of Bandit Policies—0
Meta-Information Guided Meta-Learning for Few-Shot Relation ClassificationCode0
The Advantage of Conditional Meta-Learning for Biased Regularization and Fine TuningCode0
A Closer Look at the Training Strategy for Modern Meta-LearningCode0
Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning—0
Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach—0
Learning to Select Best Forecast Tasks for Clinical Outcome Prediction—0
MATE: Plugging in Model Awareness to Task Embedding for Meta LearningCode0
OOD-MAML: Meta-Learning for Few-Shot Out-of-Distribution Detection and Classification—0
Adversarial Attacks on Deep Graph Matching—0
Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot TasksCode0
Meta learning to classify intent and slot labels with noisy few shot examples—0
Is Support Set Diversity Necessary for Meta-Learning?—0
Connecting Context-specific Adaptation in Humans to Meta-learning—0
Meta-learning in natural and artificial intelligence—0
MetaGater: Fast Learning of Conditional Channel Gated Networks via Federated Meta-Learning—0
Making Graph Neural Networks Worth It for Low-Data Molecular Machine Learning—0
Double Meta-Learning for Data Efficient Policy Optimization in Non-Stationary Environments—0
Meta Variational Monte Carlo—0
Show:102550
← PrevPage 109 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