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 2301–2325 of 3569 papers

TitleStatusHype
Learning to Continually Learn Rapidly from Few and Noisy DataCode0
Structure-Enhanced Meta-Learning For Few-Shot Graph ClassificationCode0
Meta Learning Black-Box Population-Based Optimizers—0
Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms—0
Task Aligned Generative Meta-learning for Zero-shot Learning—0
Meta-Learning with Variational BayesCode0
Domain Generalization: A Survey—0
Meta-Curriculum Learning for Domain Adaptation in Neural Machine TranslationCode1
Task-Adaptive Neural Network Search with Meta-Contrastive LearningCode1
Meta-Learning-Based Robust Adaptive Flight Control Under Uncertain Wind Conditions—0
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot LearningCode1
Universal-Prototype Enhancing for Few-Shot Object DetectionCode1
Meta-learning One-class Classifiers with Eigenvalue Solvers for Supervised Anomaly Detection—0
Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-LearningCode1
A Brief Summary of Interactions Between Meta-Learning and Self-Supervised Learning—0
Meta-Learning an Inference Algorithm for Probabilistic Programs—0
Meta-learning representations for clustering with infinite Gaussian mixture models—0
Meta-Learning with Graph Neural Networks: Methods and Applications—0
Task-adaptive Neural Process for User Cold-Start RecommendationCode1
Meta-Learning for improving rare word recognition in end-to-end ASR—0
Multi-Domain Learning by Meta-Learning: Taking Optimal Steps in Multi-Domain Loss Landscapes by Inner-Loop Learning—0
Emerging Trends in Federated Learning: From Model Fusion to Federated X Learning—0
Trajectory-Based Meta-Learning for Out-Of-Vocabulary Word Embedding Learning—0
Self-Domain Adaptation for Face Anti-Spoofing—0
Credit Assignment with Meta-Policy Gradient for Multi-Agent Reinforcement Learning—0
Show:102550
← PrevPage 93 of 143Next →
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