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 861–870 of 3569 papers

TitleStatusHype
Adaptive Mixing of Auxiliary Losses in Supervised LearningCode0
Learning to Defer to a Population: A Meta-Learning ApproachCode0
Learning to Few-Shot Learn Across Diverse Natural Language Classification TasksCode0
A Unified Meta-Learning Framework for Dynamic Transfer LearningCode0
Detecting Sockpuppetry on Wikipedia Using Meta-LearningCode0
Learning to acquire novel cognitive tasks with evolution, plasticity and meta-meta-learningCode0
Designing Time-Series Models With Hypernetworks & Adversarial PortfoliosCode0
Learning Task-Aware Energy Disaggregation: a Federated ApproachCode0
Learning to adapt: a meta-learning approach for speaker adaptationCode0
Learning One-Shot Imitation from Humans without HumansCode0
Show:102550
← PrevPage 87 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