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 1926–1950 of 3569 papers

TitleStatusHype
MMTL: The Meta Multi-Task Learning for Aspect Category Sentiment Analysis—0
Terminal Adaptive Guidance for Autonomous Hypersonic Strike Weapons via Reinforcement Learning—0
Predicting Flat-Fading Channels via Meta-Learned Closed-Form Linear Filters and Equilibrium PropagationCode0
Unsupervised Meta-Learning via Latent Space Energy-based Model of Symbol Vector Coupling—0
Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptation—0
How Neural Processes Improve Graph Link PredictionCode0
Task Relatedness-Based Generalization Bounds for Meta Learning—0
Improving Meta-Continual Learning Representations with Representation ReplayCode0
Unraveling Model-Agnostic Meta-Learning via The Adaptation Learning Rate—0
Learning Neural Processes on the Fly—0
Improved Generalization Risk Bounds for Meta-Learning with PAC-Bayes-kl Analysis—0
Fast Adaptive Anomaly Detection—0
Meta Attention For Off-Policy Actor-Critic—0
Gradient-based Meta-solving and Its Applications to Iterative Methods for Solving Differential Equations—0
PDAML: A Pseudo Domain Adaptation Paradigm for Subject-independent EEG-based Emotion Recognition—0
Do What Nature Did To Us: Evolving Plastic Recurrent Neural Networks For Generalized Tasks—0
Discrepancy-Optimal Meta-Learning for Domain Generalization—0
MDFL: A UNIFIED FRAMEWORK WITH META-DROPOUT FOR FEW-SHOT LEARNING—0
Transferring Hierarchical Structure with Dual Meta Imitation Learning—0
From Biased Data to Unbiased Models: a Meta-Learning Approach—0
Clustered Task-Aware Meta-Learning by Learning from Learning PathsCode0
ES-Based Jacobian Enables Faster Bilevel Optimization—0
FedNAS: Federated Deep Learning via Neural Architecture Search—0
Automatic Forecasting via Meta-Learning—0
Information-Aware Time Series Meta-Contrastive Learning—0
Show:102550
← PrevPage 78 of 143Next →
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