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 1031–1040 of 3569 papers

TitleStatusHype
Discrepancy-Optimal Meta-Learning for Domain Generalization—0
Automated Reinforcement Learning (AutoRL): A Survey and Open Problems—0
Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection—0
Finite-Sum Coupled Compositional Stochastic Optimization: Theory and Applications—0
Discovering Quality-Diversity Algorithms via Meta-Black-Box Optimization—0
Discovering Physics Laws of Dynamical Systems via Invariant Function Learning—0
Automated Grading of Students' Handwritten Graphs: A Comparison of Meta-Learning and Vision-Large Language Models—0
Alzheimer's Magnetic Resonance Imaging Classification Using Deep and Meta-Learning Models—0
Automated Few-Shot Time Series Forecasting based on Bi-level Programming—0
Directional Domain Generalization—0
Show:102550
← PrevPage 104 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