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 17511775 of 3569 papers

TitleStatusHype
Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity0
Few-Shot Meta Learning for Recognizing Facial Phenotypes of Genetic Disorders0
Meta-learning Pathologies from Radiology Reports using Variance Aware Prototypical Networks0
Deep domain adaptation for polyphonic melody extraction0
MetaASSIST: Robust Dialogue State Tracking with Meta LearningCode0
Low-Resource Multilingual and Zero-Shot Multispeaker TTS0
Boosting Natural Language Generation from Instructions with Meta-Learning0
Forging Multiple Training Objectives for Pre-trained Language Models via Meta-LearningCode0
Learning Transferable Adversarial Robust Representations via Multi-view Consistency0
Few-Shot Learning of Compact Models via Task-Specific Meta Distillation0
Learning to Sample and Aggregate: Few-shot Reasoning over Temporal Knowledge Graphs0
Neural Routing in Meta LearningCode0
Meta Transferring for DeblurringCode0
Multi-Task Meta Learning: learn how to adapt to unseen tasksCode0
Improving the Reliability for Confidence Estimation0
Meta-learning Based Short-Term Passenger Flow Prediction for Newly-Operated Urban Rail Transit Stations0
Few-Shot Visual Question Generation: A Novel Task and Benchmark Datasets0
Evaluated CMI Bounds for Meta Learning: Tightness and Expressiveness0
A Unified Framework with Meta-dropout for Few-shot Learning0
The Devil is in the Details: On Models and Training Regimes for Few-Shot Intent Classification0
TGDM: Target Guided Dynamic Mixup for Cross-Domain Few-Shot LearningCode0
Multi-Modal Fusion by Meta-InitializationCode0
Missing Modality meets Meta Sampling (M3S): An Efficient Universal Approach for Multimodal Sentiment Analysis with Missing Modality0
Sample-Efficient Personalization: Modeling User Parameters as Low Rank Plus Sparse Components0
Unsupervised Few-shot Learning via Deep Laplacian Eigenmaps0
Show:102550
← PrevPage 71 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