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 2301–2310 of 3569 papers

TitleStatusHype
A Lazy Approach to Long-Horizon Gradient-Based Meta-Learning—0
ALCN: Meta-Learning for Contrast Normalization Applied to Robust 3D Pose Estimation—0
Algorithm Design for Online Meta-Learning with Task Boundary Detection—0
Algorithm Selection Framework for Cyber Attack Detection—0
All in One: Multi-task Prompting for Graph Neural Networks—0
All in One: Multi-Task Prompting for Graph Neural Networks (Extended Abstract)—0
AllWOZ: Towards Multilingual Task-Oriented Dialog Systems for All—0
AllWOZ: Towards Multilingual Task-Oriented Dialog Systems for All—0
A Low-Complexity Plug-and-Play Deep Learning Model for Massive MIMO Precoding Across Sites—0
Alpha MAML: Adaptive Model-Agnostic Meta-Learning—0
Show:102550
← PrevPage 231 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