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

Showing 231240 of 3569 papers

TitleStatusHype
Reinforcement learning Based Automated Design of Differential Evolution Algorithm for Black-box Optimization0
One-Class Domain Adaptation via Meta-Learning0
DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning0
Meta-Sparsity: Learning Optimal Sparse Structures in Multi-task Networks through Meta-learning0
Collaborative Imputation of Urban Time Series through Cross-city Meta-learning0
Exploring the Efficacy of Meta-Learning: Unveiling Superior Data Diversity Utilization of MAML Over Pre-training0
Dynamic Multimodal Fusion via Meta-Learning Towards Micro-Video RecommendationCode0
Meta-Learning for Physically-Constrained Neural System Identification0
Capability-Aware Shared Hypernetworks for Flexible Heterogeneous Multi-Robot CoordinationCode0
Q-MAML: Quantum Model-Agnostic Meta-Learning for Variational Quantum AlgorithmsCode0
Show:102550
← PrevPage 24 of 357Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-train success rate97.8Unverified
2MZMeta-train success rate97.6Unverified
3MAMLMeta-test success rate36Unverified
4RL^2Meta-test success rate10Unverified
5DnCMeta-test success rate5.4Unverified
6PEARLMeta-test success rate0Unverified
#ModelMetricClaimedVerifiedStatus
1SoftModuleAverage Success Rate60Unverified
2Multi-task multi-head SACAverage Success Rate35.85Unverified
3DisCorAverage Success Rate26Unverified
4NDPAverage Success Rate11Unverified
#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-test success rate (zero-shot)18.5Unverified
2MZMeta-test success rate (zero-shot)17.7Unverified
#ModelMetricClaimedVerifiedStatus
1Metadrop% Test Accuracy95.75Unverified