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 1361–1370 of 3569 papers

TitleStatusHype
BioAct-Het: A Heterogeneous Siamese Neural Network for Bioactivity Prediction Using Novel Bioactivity RepresentatioCode0
Dynamic Link Prediction for New Nodes in Temporal Graph Networks—0
A Partially Supervised Reinforcement Learning Framework for Visual Active SearchCode0
Hypernetwork-based Meta-Learning for Low-Rank Physics-Informed Neural Networks—0
Disentangled Latent Spaces Facilitate Data-Driven Auxiliary Learning—0
In-Context Learning for Few-Shot Molecular Property Prediction—0
Subspace Adaptation Prior for Few-Shot LearningCode0
Federated Meta-Learning for Few-Shot Fault Diagnosis with Representation Encoding—0
Reset It and Forget It: Relearning Last-Layer Weights Improves Continual and Transfer Learning—0
Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters—0
Show:102550
← PrevPage 137 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