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 2426–2450 of 3569 papers

TitleStatusHype
Contextualizing Meta-Learning via Learning to DecomposeCode0
Generative Conversational Networks—0
Learning Deep Morphological Networks with Neural Architecture SearchCode0
Domain Generalization on Medical Imaging Classification using Episodic Training with Task Augmentation—0
Knowledge Consolidation based Class Incremental Online Learning with Limited Data—0
Robust Graph Meta-learning for Weakly-supervised Few-shot Node Classification—0
Meta-Learning for Symbolic Hyperparameter DefaultsCode0
Attentional Meta-learners for Few-shot Polythetic ClassificationCode0
Probabilistic task modelling for meta-learningCode0
Memory-Based Optimization Methods for Model-Agnostic Meta-Learning and Personalized Federated LearningCode0
Learning Functional Priors and Posteriors from Data and Physics—0
Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization—0
Evaluating Meta-Feature Selection for the Algorithm Recommendation ProblemCode0
RegMix: Data Mixing Augmentation for Regression—0
Meta-Learning Reliable Priors in the Function Space—0
A Meta Learning Approach to Discerning Causal Graph Structure—0
DAMSL: Domain Agnostic Meta Score-based LearningCode0
Meta-learning with implicit gradients in a few-shot setting for medical image segmentation—0
Meta-learning for downstream aware and agnostic pretraining—0
Signal Transformer: Complex-valued Attention and Meta-Learning for Signal Recognition—0
Meta-Learning with Variational Semantic Memory for Word Sense DisambiguationCode0
Minimax and Neyman-Pearson Meta-Learning for Outlier LanguagesCode0
DReCa: A General Task Augmentation Strategy for Few-Shot Natural Language Inference—0
Information-Theoretic Analysis of Epistemic Uncertainty in Bayesian Meta-learning—0
Modality-specific Distillation—0
Show:102550
← PrevPage 98 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