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 3441–3450 of 3569 papers

TitleStatusHype
Shaping Visual Representations with Language for Few-shot ClassificationCode0
Finetuning-Activated Backdoors in LLMsCode0
Adaptive Meta-Domain Transfer Learning (AMDTL): A Novel Approach for Knowledge Transfer in AICode0
Meta-Learning with Generalized Ridge Regression: High-dimensional Asymptotics, Optimality and Hyper-covariance EstimationCode0
Persian Natural Language Inference: A Meta-learning approachCode0
Meta-Learning with Hessian-Free Approach in Deep Neural Nets TrainingCode0
Automatic selection of clustering algorithms using supervised graph embeddingCode0
Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary DataCode0
AALF: Almost Always Linear ForecastingCode0
Personalized Algorithm Generation: A Case Study in Learning ODE IntegratorsCode0
Show:102550
← PrevPage 345 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