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 2991–3000 of 3569 papers

TitleStatusHype
MATE: Plugging in Model Awareness to Task Embedding for Meta LearningCode0
A Stylometric Inquiry into Hyperpartisan and Fake NewsCode0
Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware SubspaceCode0
Structured Prediction for Conditional Meta-LearningCode0
Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal PredictionCode0
Recurrent machines for likelihood-free inferenceCode0
Mixup-Augmented Meta-Learning for Sample-Efficient Fine-Tuning of Protein SimulatorsCode0
Recurrent Meta-Learning against Generalized Cold-start Problem in CTR PredictionCode0
Stateless Neural Meta-Learning using Second-Order GradientsCode0
Capability-Aware Shared Hypernetworks for Flexible Heterogeneous Multi-Robot CoordinationCode0
Show:102550
← PrevPage 300 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