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 2271–2280 of 3569 papers

TitleStatusHype
Advances and Challenges in Meta-Learning: A Technical Review—0
Advancing Extrapolative Predictions of Material Properties through Learning to Learn—0
AdverSAR: Adversarial Search and Rescue via Multi-Agent Reinforcement Learning—0
Adversarial Attacks are a Surprisingly Strong Baseline for Poisoning Few-Shot Meta-Learners—0
Adversarial Attacks on Deep Graph Matching—0
Adversarial Constrained Bidding via Minimax Regret Optimization with Causality-Aware Reinforcement Learning—0
Adversarial Meta-Learning—0
Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition—0
A Dynamic Meta-Learning Model for Time-Sensitive Cold-Start Recommendations—0
A Feature Subset Selection Algorithm Automatic Recommendation Method—0
Show:102550
← PrevPage 228 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