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 2751–2760 of 3569 papers

TitleStatusHype
Dataset Meta-Learning from Kernel Ridge-Regression—0
Learning to Actively Learn: A Robust Approach—0
System Identification via Meta-Learning in Linear Time-Varying Environments—0
How Does the Task Landscape Affect MAML Performance?—0
Meta-Learning for Neural Relation Classification with Distant Supervision—0
A Survey on Curriculum Learning—0
Modeling and Optimization Trade-off in Meta-learningCode0
Pre-training with Meta Learning for Chinese Word Segmentation—0
Learning to Optimise General TSP Instances—0
Meta-Learning for Domain Generalization in Semantic Parsing—0
Show:102550
← PrevPage 276 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