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

Showing 251300 of 3569 papers

TitleStatusHype
DIMES: A Differentiable Meta Solver for Combinatorial Optimization ProblemsCode1
Diffusion-Based Neural Network Weights GenerationCode1
An Analysis of the Adaptation Speed of Causal ModelsCode1
DIP: Unsupervised Dense In-Context Post-training of Visual RepresentationsCode1
Exploration in Approximate Hyper-State Space for Meta Reinforcement LearningCode1
Exploiting Shared Representations for Personalized Federated LearningCode1
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot LearningCode1
Evolving Reinforcement Learning AlgorithmsCode1
Evading Forensic Classifiers with Attribute-Conditioned Adversarial FacesCode1
Expanding the Deployment Envelope of Behavior Prediction via Adaptive Meta-LearningCode1
Exploring Effective Factors for Improving Visual In-Context LearningCode1
Empirical Bayes Transductive Meta-Learning with Synthetic GradientsCode1
Efficient Graph Deep Learning in TensorFlow with tf_geometricCode1
End-to-End Fast Training of Communication Links Without a Channel Model via Online Meta-LearningCode1
Attentive Weights Generation for Few Shot Learning via Information MaximizationCode1
Attentional-Biased Stochastic Gradient DescentCode1
Auto-Lambda: Disentangling Dynamic Task RelationshipsCode1
EEG-Reptile: An Automatized Reptile-Based Meta-Learning Library for BCIsCode1
Efficient Automatic Tuning for Data-driven Model Predictive Control via Meta-LearningCode1
On the Convergence Theory for Hessian-Free Bilevel AlgorithmsCode1
Exploring Task Difficulty for Few-Shot Relation ExtractionCode1
An Accurate and Fully-Automated Ensemble Model for Weekly Time Series ForecastingCode1
A Structured Dictionary Perspective on Implicit Neural RepresentationsCode1
Attention Guided Cosine Margin For Overcoming Class-Imbalance in Few-Shot Road Object DetectionCode1
AutoInit: Analytic Signal-Preserving Weight Initialization for Neural NetworksCode1
Efficient Domain Generalization via Common-Specific Low-Rank DecompositionCode1
Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled DataCode1
AutoDebias: Learning to Debias for RecommendationCode1
Automated Machine Learning Techniques for Data StreamsCode1
Automated Relational Meta-learningCode1
DPGN: Distribution Propagation Graph Network for Few-shot LearningCode1
EvoGrad: Efficient Gradient-Based Meta-Learning and Hyperparameter OptimizationCode1
Automating Outlier Detection via Meta-LearningCode1
Exploiting Domain-Specific Features to Enhance Domain GeneralizationCode1
Adversarial Feature Augmentation for Cross-domain Few-shot ClassificationCode1
Automating Continual LearningCode1
BlackGoose Rimer: Harnessing RWKV-7 as a Simple yet Superior Replacement for Transformers in Large-Scale Time Series ModelingCode1
Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot LearningCode1
A Physics-Informed Meta-Learning Framework for the Continuous Solution of Parametric PDEs on Arbitrary GeometriesCode1
A picture of the space of typical learnable tasksCode1
Dual Adaptive Representation Alignment for Cross-domain Few-shot LearningCode1
Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive ProcessesCode1
Adv-Makeup: A New Imperceptible and Transferable Attack on Face RecognitionCode1
Faster Meta Update Strategy for Noise-Robust Deep LearningCode1
Dynamic Relevance Learning for Few-Shot Object DetectionCode1
AwesomeMeta+: A Mixed-Prototyping Meta-Learning System Supporting AI Application Design AnywhereCode1
Bag of Tricks for Long-Tailed Visual Recognition with Deep Convolutional Neural NetworksCode1
Few-shot Classification via Adaptive AttentionCode1
Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot RelationsCode1
DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend ForecastingCode1
Show:102550
← PrevPage 6 of 72Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-train success rate97.8Unverified
2MZMeta-train success rate97.6Unverified
3MAMLMeta-test success rate36Unverified
4RL^2Meta-test success rate10Unverified
5DnCMeta-test success rate5.4Unverified
6PEARLMeta-test success rate0Unverified
#ModelMetricClaimedVerifiedStatus
1SoftModuleAverage Success Rate60Unverified
2Multi-task multi-head SACAverage Success Rate35.85Unverified
3DisCorAverage Success Rate26Unverified
4NDPAverage Success Rate11Unverified
#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-test success rate (zero-shot)18.5Unverified
2MZMeta-test success rate (zero-shot)17.7Unverified
#ModelMetricClaimedVerifiedStatus
1Metadrop% Test Accuracy95.75Unverified