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 1051–1100 of 3569 papers

TitleStatusHype
Meta-Learning Guided Label Noise Distillation for Robust Signal Modulation Classification—0
FewShotNeRF: Meta-Learning-based Novel View Synthesis for Rapid Scene-Specific Adaptation—0
Learn To Learn More Precisely—0
A Blockchain-based Reliable Federated Meta-learning for Metaverse: A Dual Game Framework—0
Learning to Learn without Forgetting using AttentionCode0
Few-shot Scooping Under Domain Shift via Simulated Maximal Deployment Gaps—0
MetaWearS: A Shortcut in Wearable Systems Lifecycle with Only a Few Shots—0
Analyzing the Effectiveness of Quantum Annealing with Meta-LearningCode0
Black box meta-learning intrinsic rewards for sparse-reward environmentsCode0
Neuromorphic on-chip reservoir computing with spiking neural network architectures—0
TalaGen: A System for Automatic Tala Identification and Generation—0
Meta-Learning for Adaptive Control with Automated Mirror Descent—0
Designing Time-Series Models With Hypernetworks & Adversarial PortfoliosCode0
Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation—0
Bayesian meta learning for trustworthy uncertainty quantification—0
Few-Shot Medical Image Segmentation with Large Kernel Attention—0
Optimal Hessian/Jacobian-Free Nonconvex-PL Bilevel Optimization—0
Train-Attention: Meta-Learning Where to Focus in Continual Knowledge LearningCode0
A Comprehensive Review of Few-shot Action Recognition—0
Meta-GPS++: Enhancing Graph Meta-Learning with Contrastive Learning and Self-TrainingCode0
MetaAug: Meta-Data Augmentation for Post-Training QuantizationCode0
Adaptive Uncertainty Quantification for Scenario-based Control Using Meta-learning of Bayesian Neural Networks—0
Enhancing Graph Neural Networks with Limited Labeled Data by Actively Distilling Knowledge from Large Language Models—0
A Comprehensive Sustainable Framework for Machine Learning and Artificial Intelligence—0
Information-Theoretic Foundations for Machine Learning—0
Base Models for Parabolic Partial Differential EquationsCode0
Adaptive Cascading Network for Continual Test-Time AdaptationCode0
An Evaluation of Continual Learning for Advanced Node Semiconductor Defect Inspection—0
A Meta-Learning Approach for Multi-Objective Reinforcement Learning in Sustainable Home Environments—0
Siamese Transformer Networks for Few-shot Image Classification—0
Efficient In-Context Medical Segmentation with Meta-driven Visual Prompt Selection—0
Learning to Unlearn for Robust Machine Unlearning—0
Warming Up Cold-Start CTR Prediction by Learning Item-Specific Feature Interactions—0
A Self-Supervised Learning Pipeline for Demographically Fair Facial Attribute Classification—0
Generalized Face Anti-spoofing via Finer Domain Partition and Disentangling Liveness-irrelevant FactorsCode0
MLRS-PDS: A Meta-learning recommendation of dynamic ensemble selection pipelinesCode0
DMSD-CDFSAR: Distillation from Mixed-Source Domain for Cross-Domain Few-shot Action Recognition—0
EMPL: A novel Efficient Meta Prompt Learning Framework for Few-shot Unsupervised Domain Adaptation—0
Meta-Learning and representation learner: A short theoretical note—0
Artificial Inductive Bias for Synthetic Tabular Data Generation in Data-Scarce ScenariosCode0
Pushing the Boundary: Specialising Deep Configuration Performance Learning—0
Meta-Learning Based Optimization for Large Scale Wireless Systems—0
GM-DF: Generalized Multi-Scenario Deepfake DetectionCode0
Meta Learning for Efficient Fine-Tuning of Large Language ModelsCode0
Learning Modality Knowledge Alignment for Cross-Modality Transfer—0
Toward Universal Medical Image Registration via Sharpness-Aware Meta-Continual LearningCode0
Exploring Cross-Domain Few-Shot Classification via Frequency-Aware PromptingCode0
Meta-learning and Data Augmentation for Stress Testing Forecasting ModelsCode0
Meta-GCN: A Dynamically Weighted Loss Minimization Method for Dealing with the Data Imbalance in Graph Neural Networks—0
Automated Privacy-Preserving Techniques via Meta-LearningCode0
Show:102550
← PrevPage 22 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