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 1281–1290 of 3569 papers

TitleStatusHype
Federated Learning and Meta Learning: Approaches, Applications, and Directions—0
Meta Learning of Interface Conditions for Multi-Domain Physics-Informed Neural Networks—0
Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity—0
Few-Shot Meta Learning for Recognizing Facial Phenotypes of Genetic Disorders—0
MetaEMS: A Meta Reinforcement Learning-based Control Framework for Building Energy Management System—0
Meta-learning Pathologies from Radiology Reports using Variance Aware Prototypical Networks—0
Deep domain adaptation for polyphonic melody extraction—0
MetaASSIST: Robust Dialogue State Tracking with Meta LearningCode0
Low-Resource Multilingual and Zero-Shot Multispeaker TTS—0
m^4Adapter: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-AdapterCode1
Show:102550
← PrevPage 129 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