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 251275 of 3569 papers

TitleStatusHype
MetaTPTrans: A Meta Learning Approach for Multilingual Code Representation LearningCode1
Data-Efficient Brain Connectome Analysis via Multi-Task Meta-LearningCode1
Sharp-MAML: Sharpness-Aware Model-Agnostic Meta LearningCode1
Neural Diffusion ProcessesCode1
GenSDF: Two-Stage Learning of Generalizable Signed Distance FunctionsCode1
HyperMAML: Few-Shot Adaptation of Deep Models with HypernetworksCode1
MetaSSD: Meta-Learned Self-Supervised DetectionCode1
Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge TransferCode1
Meta-Learning Based Knowledge Extrapolation for Knowledge Graphs in the Federated SettingCode1
Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property PredictionCode1
Unsupervised Meta Learning With Multiview Constraints for Hyperspectral Image Small Sample set ClassificationCode1
Learn to Adapt for Generalized Zero-Shot Text ClassificationCode1
Learning to Scaffold: Optimizing Model Explanations for TeachingCode1
Beyond the Prototype: Divide-and-conquer Proxies for Few-shot SegmentationCode1
Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a DifferenceCode1
Self-Guided Learning to Denoise for Robust RecommendationCode1
Control-oriented meta-learningCode1
Pin the Memory: Learning to Generalize Semantic SegmentationCode1
MetaAudio: A Few-Shot Audio Classification BenchmarkCode1
Few-Shot Class-Incremental Learning by Sampling Multi-Phase TasksCode1
Learning to Adapt to Unseen Abnormal Activities under Weak SupervisionCode1
Cross-Domain Few-Shot Semantic SegmentationCode1
Predicting Multi-Antenna Frequency-Selective Channels via Meta-Learned Linear Filters based on Long-Short Term Channel DecompositionCode1
Pre-training to Match for Unified Low-shot Relation ExtractionCode1
Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot LearningCode1
Show:102550
← PrevPage 11 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