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 2131–2140 of 3569 papers

TitleStatusHype
Unsupervised Intuitive Physics from Past Experiences—0
Unsupervised Learning of Hybrid Latent Dynamics: A Learn-to-Identify Framework—0
Unsupervised Learning via Meta-Learning—0
Unsupervised Meta-Learning For Few-Shot Image Classification—0
Unsupervised Meta Learning for One Shot Title Compression in Voice Commerce—0
Unsupervised Meta-Learning for Reinforcement Learning—0
Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models—0
Unsupervised Meta-Learning via In-Context Learning—0
Unsupervised Meta-Learning via Latent Space Energy-based Model of Symbol Vector Coupling—0
UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis—0
Show:102550
← PrevPage 214 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