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 19762000 of 3569 papers

TitleStatusHype
Multimodality in Meta-Learning: A Comprehensive Survey0
ST-MAML: A Stochastic-Task based Method for Task-Heterogeneous Meta-Learning0
An Enhanced Span-based Decomposition Method for Few-Shot Sequence LabelingCode1
Learning to Selectively Learn for Weakly-supervised Paraphrase Generation0
Introducing Symmetries to Black Box Meta Reinforcement Learning0
A Meta-Learning Approach for Training Explainable Graph Neural NetworksCode1
AutoInit: Analytic Signal-Preserving Weight Initialization for Neural NetworksCode1
MetaMedSeg: Volumetric Meta-learning for Few-Shot Organ SegmentationCode0
Meta-Learning with Sparse Experience Replay for Lifelong Language Learning0
Semi-Supervised Few-Shot Intent Classification and Slot Filling0
Few-Shot Object Detection by Attending to Per-Sample-Prototype0
Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGDCode0
Partner-Assisted Learning for Few-Shot Image Classification0
Should We Be Pre-training? An Argument for End-task Aware Training as an AlternativeCode0
Gradient Imitation Reinforcement Learning for Low Resource Relation ExtractionCode1
Few-shot Quality-Diversity OptimizationCode0
One-Class Meta-Learning: Towards Generalizable Few-Shot Open-Set Classification0
Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning0
Cross-Market Product RecommendationCode1
Leveraging Table Content for Zero-shot Text-to-SQL with Meta-LearningCode1
Exploring Task Difficulty for Few-Shot Relation ExtractionCode1
Knowledge-Aware Meta-learning for Low-Resource Text ClassificationCode1
Rapid Model Architecture Adaption for Meta-Learning0
Bootstrapped Meta-LearningCode0
Integrated and Adaptive Guidance and Control for Endoatmospheric Missiles via Reinforcement Learning0
Show:102550
← PrevPage 80 of 143Next →

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