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 1061–1070 of 3569 papers

TitleStatusHype
Differentiable Meta-Learning of Bandit Policies—0
A Low-Complexity Plug-and-Play Deep Learning Model for Massive MIMO Precoding Across Sites—0
Differentiable Meta-learning Model for Few-shot Semantic Segmentation—0
Meta-Learning Bandit Policies by Gradient Ascent—0
Differentiable Bandit Exploration—0
Auto-CASH: Autonomous Classification Algorithm Selection with Deep Q-Network—0
A Universal Knowledge Model and Cognitive Architecture for Prototyping AGI—0
DIAMOND: Taming Sample and Communication Complexities in Decentralized Bilevel Optimization—0
A CMDP-within-online framework for Meta-Safe Reinforcement Learning—0
From Text to Treatment Effects: A Meta-Learning Approach to Handling Text-Based Confounding—0
Show:102550
← PrevPage 107 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