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 2011–2020 of 3569 papers

TitleStatusHype
Prototype-Guided Memory Replay for Continual Learning—0
Provable Generalization of Overparameterized Meta-learning Trained with SGD—0
Provable Hierarchy-Based Meta-Reinforcement Learning—0
Provable Multi-Party Reinforcement Learning with Diverse Human Feedback—0
Provably Efficient Model-based Policy Adaptation—0
Provably Faster Algorithms for Bilevel Optimization and Applications to Meta-Learning—0
Provably Safe Model-Based Meta Reinforcement Learning: An Abstraction-Based Approach—0
Pushing the Boundary: Specialising Deep Configuration Performance Learning—0
Putting Theory to Work: From Learning Bounds to Meta-Learning Algorithms—0
qNBO: quasi-Newton Meets Bilevel Optimization—0
Show:102550
← PrevPage 202 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