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 2381–2390 of 3569 papers

TitleStatusHype
Enhanced Bilevel Optimization via Bregman Distance—0
Subgraph-aware Few-Shot Inductive Link Prediction via Meta-Learning—0
A novel meta-learning initialization method for physics-informed neural networks—0
Improving the Generalization of Meta-learning on Unseen Domains via Adversarial Shift—0
Soft Layer Selection with Meta-Learning for Zero-Shot Cross-Lingual Transfer—0
Learn2Hop: Learned Optimization on Rough Landscapes—0
Algorithm Selection on a Meta LevelCode0
PICASO: Permutation-Invariant Cascaded Attentional Set OperatorCode0
Property-Aware Relation Networks for Few-Shot Molecular Property Prediction—0
Next-item Recommendations in Short Sessions—0
Show:102550
← PrevPage 239 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