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 2826–2850 of 3569 papers

TitleStatusHype
Fast Adaptation with Kernel and Gradient based Meta Leaning—0
Fast Adaptation with Meta-Reinforcement Learning for Trust Modelling in Human-Robot Interaction—0
Fast-adapting and Privacy-preserving Federated Recommender System—0
Fast Adaptive Anomaly Detection—0
Fast Adaptive Federated Bilevel Optimization—0
Fast and Effective Adaptation of Facial Action Unit Detection Deep Model—0
Fast and Scalable Human Pose Estimation using mmWave Point Cloud—0
Fast and Slow Learning of Recurrent Independent Mechanisms—0
Fast Data-Driven Adaptation of Radar Detection via Meta-Learning—0
Faster Adaptive Momentum-Based Federated Methods for Distributed Composition Optimization—0
Faster Optimization-Based Meta-Learning Adaptation Phase—0
Fast Image Classification by Boosting Fuzzy Classifiers—0
Fast Medical Shape Reconstruction via Meta-learned Implicit Neural Representations—0
Fast On-Device Adaptation for Spiking Neural Networks via Online-Within-Online Meta-Learning—0
Fast Power Control Adaptation via Meta-Learning for Random Edge Graph Neural Networks—0
Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizes—0
Fast & Slow Learning: Incorporating Synthetic Gradients in Neural Memory Controllers—0
Fast Training Method for Stochastic Compositional Optimization Problems—0
Fast Training Method for Stochastic Compositional Optimization Problems—0
Fast Training of Neural Lumigraph Representations using Meta Learning—0
FDNAS: Improving Data Privacy and Model Diversity in AutoML—0
Feature-context driven Federated Meta-Learning for Rare Disease Prediction—0
Federated Learning and Meta Learning: Approaches, Applications, and Directions—0
Federated Conditional Stochastic Optimization—0
A Benchmark for Federated Hetero-Task Learning—0
Show:102550
← PrevPage 114 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