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 1161–1170 of 3569 papers

TitleStatusHype
Adaptive Ensemble Learning: Boosting Model Performance through Intelligent Feature Fusion in Deep Neural Networks—0
Group Equivariant Conditional Neural Processes—0
Guided Meta-Policy Search—0
How Important is the Train-Validation Split in Meta-Learning?—0
A Survey on Knowledge Editing of Neural Networks—0
Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity—0
A Knowledge-Driven Meta-Learning Method for CSI Feedback—0
Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks—0
Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning—0
A Survey on Few-Shot Class-Incremental Learning—0
Show:102550
← PrevPage 117 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