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 2181–2190 of 3569 papers

TitleStatusHype
UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis—0
Unsupervised Domain Adaptation for Event Detection via Meta Self-Paced Learning—0
MAML-CL: Edited Model-Agnostic Meta-Learning for Continual LearningCode0
A Self-Adaptive Learning Rate and Curriculum Learning Based Framework for Few-Shot Text Classification—0
Meta-learning via Language Model In-context Tuning—0
Persian Natural Language Inference: A Meta-learning approach—0
MetaPrompting: Learning to Learn Better Prompts—0
ST-SQL: Semi-Supervised Self-Training for Text-to-SQL via Column Specificity Meta-LearningCode0
A Meta-Learning Approach for Few-Shot (Dis)Agreement Identification in Online Discussions—0
Meta-Adapter: Parameter Efficient Few-Shot Learning through Meta-Learning—0
Show:102550
← PrevPage 219 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