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 2401–2410 of 3569 papers

TitleStatusHype
A Simple Meta-learning Paradigm for Zero-shot Intent Classification with Mixture Attention Mechanism—0
A Simple Recipe to Meta-Learn Forward and Backward Transfer—0
Supervised Graph Contrastive Learning for Few-shot Node Classification—0
A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm—0
A Single-Timescale Method for Stochastic Bilevel Optimization—0
Assessing two novel distance-based loss functions for few-shot image classification—0
Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation—0
A statistical physics framework for optimal learning—0
A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learning—0
A Student-Teacher Architecture for Dialog Domain Adaptation under the Meta-Learning Setting—0
Show:102550
← PrevPage 241 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