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 1461–1470 of 3569 papers

TitleStatusHype
All in One: Multi-task Prompting for Graph Neural Networks—0
Model-Assisted Probabilistic Safe Adaptive Control With Meta-Bayesian Learning—0
OpenClinicalAI: An Open and Dynamic Model for Alzheimer's Disease Diagnosis—0
Elastically-Constrained Meta-Learner for Federated Learning—0
AutoML in Heavily Constrained ApplicationsCode0
A Meta-Learning Method for Estimation of Causal Excursion Effects to Assess Time-Varying ModerationCode0
Contrastive Meta-Learning for Few-shot Node ClassificationCode0
Safe Navigation in Unstructured Environments by Minimizing Uncertainty in Control and Perception—0
Near-Optimal Nonconvex-Strongly-Convex Bilevel Optimization with Fully First-Order Oracles—0
Is Pre-training Truly Better Than Meta-Learning?—0
Show:102550
← PrevPage 147 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