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 1101–1150 of 3569 papers

TitleStatusHype
Learning New Tasks from a Few Examples with Soft-Label PrototypesCode0
Consistency of Compositional Generalization across Multiple LevelsCode0
Learning Low-Dimensional Embeddings for Black-Box OptimizationCode0
Learning Invariances for Policy GeneralizationCode0
Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal PredictionCode0
Approximately Equivariant Neural ProcessesCode0
ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement LearningCode0
Capability-Aware Shared Hypernetworks for Flexible Heterogeneous Multi-Robot CoordinationCode0
Learning Generalized Zero-Shot Learners for Open-Domain Image GeolocalizationCode0
Learning to Self-Train for Semi-Supervised Few-Shot ClassificationCode0
Adversarial Monte Carlo Meta-Learning of Optimal Prediction ProceduresCode0
Learning Deep Morphological Networks with Neural Architecture SearchCode0
Learning Fast Adaptation with Meta Strategy OptimizationCode0
Concurrent Meta Reinforcement LearningCode0
Concept-free Causal Disentanglement with Variational Graph Auto-EncoderCode0
Comprehensive Fair Meta-learned Recommender SystemCode0
Adaptation-Agnostic Meta-TrainingCode0
Learning advisor networks for noisy image classificationCode0
Learning an Explicit Hyperparameter Prediction Function Conditioned on TasksCode0
Learning How to Demodulate from Few Pilots via Meta-LearningCode0
Learning to Continually Learn Rapidly from Few and Noisy DataCode0
Learning to Multi-Task by Active SamplingCode0
Latent Representation Learning of Multi-scale Thermophysics: Application to Dynamics in Shocked Porous Energetic MaterialCode0
Latent-Optimized Adversarial Neural Transfer for Sarcasm DetectionCode0
Latent Task-Specific Graph Network SimulatorsCode0
Component-Based Fairness in Face Attribute Classification with Bayesian Network-informed Meta LearningCode0
Latent Bottlenecked Attentive Neural ProcessesCode0
Layer-compensated Pruning for Resource-constrained Convolutional Neural NetworksCode0
LabelCraft: Empowering Short Video Recommendations with Automated Label CraftingCode0
Few-shot Node Classification with Extremely Weak SupervisionCode0
Knowledge-enhanced Relation Graph and Task Sampling for Few-shot Molecular Property PredictionCode0
Joint Optimization of Class-Specific Training- and Test-Time Data Augmentation in SegmentationCode0
An Unsupervised Cross-Modal Hashing Method Robust to Noisy Training Image-Text Correspondences in Remote SensingCode0
Joint inference and input optimization in equilibrium networksCode0
Knowledge Distillation with Reptile Meta-Learning for Pretrained Language Model CompressionCode0
An Ensemble of Epoch-wise Empirical Bayes for Few-shot LearningCode0
Is Bayesian Model-Agnostic Meta Learning Better than Model-Agnostic Meta Learning, Provably?Code0
Comparing the Efficacy of Fine-Tuning and Meta-Learning for Few-Shot Policy ImitationCode0
Compare More Nuanced:Pairwise Alignment Bilinear Network For Few-shot Fine-grained LearningCode0
Anti-Retroactive Interference for Lifelong LearningCode0
Interval Bound Interpolation for Few-shot Learning with Few TasksCode0
Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning ApproachCode0
Inverse Learning with Extremely Sparse Feedback for RecommendationCode0
Interpretable Meta-Measure for Model PerformanceCode0
Investigating Large Language Models for Complex Word Identification in Multilingual and Multidomain SetupsCode0
It HAS to be Subjective: Human Annotator Simulation via Zero-shot Density EstimationCode0
Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image RecognitionCode0
A Partially Supervised Reinforcement Learning Framework for Visual Active SearchCode0
Few-shot Quality-Diversity OptimizationCode0
Incremental Few-Shot Learning with Attention Attractor NetworksCode0
Show:102550
← PrevPage 23 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