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 2291–2300 of 3569 papers

TitleStatusHype
Loss Function Learning for Domain Generalization by Implicit Gradient—0
Meta Learning with Minimax Regularization—0
Minimizing Memorization in Meta-learning: A Causal Perspective—0
Gradient-based Meta-solving and Its Applications to Iterative Methods for Solving Differential Equations—0
Meta-OLE: Meta-learned Orthogonal Low-Rank Embedding—0
PDAML: A Pseudo Domain Adaptation Paradigm for Subject-independent EEG-based Emotion Recognition—0
Early-Stopping for Meta-Learning: Estimating Generalization from the Activation Dynamics—0
Dynamic Regret Analysis for Online Meta-Learning—0
Improving Meta-Continual Learning Representations with Representation ReplayCode0
Multi-Subspace Structured Meta-Learning—0
Show:102550
← PrevPage 230 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