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 1911–1920 of 3569 papers

TitleStatusHype
Future Trends for Human-AI Collaboration: A Comprehensive Taxonomy of AI/AGI Using Multiple Intelligences and Learning Styles—0
A Distribution-Dependent Analysis of Meta-Learning—0
On Parameter Tuning in Meta-learning for Computer Vision—0
On Stability and Generalization of Bilevel Optimization Problem—0
On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval—0
On the Communication Complexity of Decentralized Bilevel Optimization—0
On the Convergence of Adam-Type Algorithm for Bilevel Optimization under Unbounded Smoothness—0
On the Convergence of No-Regret Learning Dynamics in Time-Varying Games—0
On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithms—0
On the Convergence Theory of Meta Reinforcement Learning with Personalized Policies—0
Show:102550
← PrevPage 192 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