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 1451–1460 of 3569 papers

TitleStatusHype
Writer adaptation for offline text recognition: An exploration of neural network-based methodsCode0
Advances and Challenges in Meta-Learning: A Technical Review—0
Semi Supervised Meta Learning for Spatiotemporal Learning—0
CognitiveNet: Enriching Foundation Models with Emotions and Awareness—0
Stability and Generalization of Stochastic Compositional Gradient Descent Algorithms—0
MALIBO: Meta-learning for Likelihood-free Bayesian OptimizationCode0
LogitMat : Zeroshot Learning Algorithm for Recommender Systems without Transfer Learning or Pretrained Models—0
Meta Federated Reinforcement Learning for Distributed Resource Allocation—0
Meta-Learning Adversarial Bandit Algorithms—0
Personalized Federated Learning via Amortized Bayesian Meta-Learning—0
Show:102550
← PrevPage 146 of 357Next →
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