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 2901–2950 of 3569 papers

TitleStatusHype
Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networksCode0
Learning to Defer to a Population: A Meta-Learning ApproachCode0
Comprehensive Fair Meta-learned Recommender SystemCode0
Reevaluating Meta-Learning Optimization Algorithms Through Contextual Self-ModulationCode0
Q-MAML: Quantum Model-Agnostic Meta-Learning for Variational Quantum AlgorithmsCode0
Spectral Convolutional Conditional Neural ProcessesCode0
Learning to Customize Model Structures for Few-shot Dialogue Generation TasksCode0
Component-Based Fairness in Face Attribute Classification with Bayesian Network-informed Meta LearningCode0
Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning ApproachCode0
Algorithm Selection on a Meta LevelCode0
Exploring the Similarity of Representations in Model-Agnostic Meta-LearningCode0
Exploring the similarity of medical imaging classification problemsCode0
Exploring Frequencies via Feature Mixing and Meta-Learning for Improving Adversarial TransferabilityCode0
The least-control principle for local learning at equilibriumCode0
LeMON: Learning to Learn Multi-Operator NetworksCode0
Meta Transferring for DeblurringCode0
Two Sides of Meta-Learning Evaluation: In vs. Out of DistributionCode0
MetaTroll: Few-shot Detection of State-Sponsored Trolls with Transformer AdaptersCode0
Comparing the Efficacy of Fine-Tuning and Meta-Learning for Few-Shot Policy ImitationCode0
Query-efficient Meta Attack to Deep Neural NetworksCode0
Inductive-Associative Meta-learning Pipeline with Human Cognitive Patterns for Unseen Drug-Target Interaction PredictionCode0
Exploring Few-Shot Defect Segmentation in General Industrial Scenarios with Metric Learning and Vision Foundation ModelsCode0
Learning to Segment Medical Images from Few-Shot Sparse LabelsCode0
An Unsupervised Cross-Modal Hashing Method Robust to Noisy Training Image-Text Correspondences in Remote SensingCode0
Learning to Continually Learn Rapidly from Few and Noisy DataCode0
RAFIC: Retrieval-Augmented Few-shot Image ClassificationCode0
Exploring Cross-Domain Few-Shot Classification via Frequency-Aware PromptingCode0
Adversarial Meta-Learning of Gamma-Minimax Estimators That Leverage Prior KnowledgeCode0
LGM-Net: Learning to Generate Matching Networks for Few-Shot LearningCode0
L-HYDRA: Multi-Head Physics-Informed Neural NetworksCode0
LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing PlatformsCode0
Lifelong Domain Word Embedding via Meta-LearningCode0
Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot LearningCode0
RAMario: Experimental Approach to Reptile Algorithm -- Reinforcement Learning for MarioCode0
MetaUE: Model-based Meta-learning for Underwater Image EnhancementCode0
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution TasksCode0
Lightweight Conditional Model Extrapolation for Streaming Data under Class-Prior ShiftCode0
Modeling Human Exploration Through Resource-Rational Reinforcement LearningCode0
Learning to adapt: a meta-learning approach for speaker adaptationCode0
Spuriousness-Aware Meta-Learning for Learning Robust ClassifiersCode0
AI-Driven Discovery of High Performance Polymer Electrodes for Next-Generation BatteriesCode0
Dynamic Subgoal-based Exploration via Bayesian OptimizationCode0
A Hierarchical Bayesian Model for Deep Few-Shot Meta LearningCode0
Local Nonparametric Meta-LearningCode0
Compare More Nuanced:Pairwise Alignment Bilinear Network For Few-shot Fine-grained LearningCode0
A Greedy Approach to Adapting the Trace Parameter for Temporal Difference LearningCode0
Exploiting Meta-Learning-based Poisoning Attacks for Graph Link PredictionCode0
A Generalised Deep Meta-Learning Model for Automated Quality Control of Cardiovascular Magnetic Resonance ImagesCode0
Long-term Cross Adversarial Training: A Robust Meta-learning Method for Few-shot Classification TasksCode0
Learning to acquire novel cognitive tasks with evolution, plasticity and meta-meta-learningCode0
Show:102550
← PrevPage 59 of 72Next →
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