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 1771–1780 of 3569 papers

TitleStatusHype
AllWOZ: Towards Multilingual Task-Oriented Dialog Systems for All—0
Improving Both Domain Robustness and Domain Adaptability in Machine TranslationCode0
How to Learn and Represent Abstractions: An Investigation using Symbolic AlchemyCode0
Leaping Through Time with Gradient-based Adaptation for RecommendationCode0
Learning to Learn Transferable AttackCode0
PMFL: Partial Meta-Federated Learning for heterogeneous tasks and its applications on real-world medical recordsCode0
CoMPS: Continual Meta Policy Search—0
MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance—0
Curriculum Meta-Learning for Few-shot ClassificationCode0
Noether Networks: Meta-Learning Useful Conserved Quantities—0
Show:102550
← PrevPage 178 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