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 1141–1150 of 3569 papers

TitleStatusHype
Zero-shot causal learningCode0
Meta Temporal Point ProcessesCode0
Meta-Learning Mini-Batch Risk Functionals—0
Invariant Meta Learning for Out-of-Distribution Generalization—0
On the Convergence of No-Regret Learning Dynamics in Time-Varying Games—0
Rewarded meta-pruning: Meta Learning with Rewards for Channel PruningCode0
Exploiting Style Transfer-based Task Augmentation for Cross-Domain Few-Shot Learning—0
Concept Discovery for Fast Adapatation—0
Foresee What You Will Learn: Data Augmentation for Domain Generalization in Non-stationary EnvironmentCode0
Improve Noise Tolerance of Robust Loss via Noise-Awareness—0
Show:102550
← PrevPage 115 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