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 941–950 of 3569 papers

TitleStatusHype
Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph GenerationCode0
DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend ForecastingCode1
Meta Generative Flow Networks with Personalization for Task-Specific Adaptation—0
Stochastic Re-weighted Gradient Descent via Distributionally Robust Optimization—0
Inductive Linear Probing for Few-shot Node Classification—0
Improving Generalization in Meta-Learning via Meta-Gradient AugmentationCode0
Few-shot Multi-domain Knowledge Rearming for Context-aware Defence against Advanced Persistent Threats—0
Adversarial Constrained Bidding via Minimax Regret Optimization with Causality-Aware Reinforcement Learning—0
Adaptive Multi-Teacher Knowledge Distillation with Meta-LearningCode1
Virtual Node Tuning for Few-shot Node Classification—0
Show:102550
← PrevPage 95 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