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 3051–3075 of 3569 papers

TitleStatusHype
MetaSelector: Meta-Learning for Recommendation with User-Level Adaptive Model Selection—0
Deep learning generates custom-made logistic regression models for explaining how breast cancer subtypes are classified—0
A meta-algorithm for classification using random recursive tree ensembles: A high energy physics application—0
Extracting more from boosted decision trees: A high energy physics case study—0
IoT Network Behavioral Fingerprint Inference with Limited Network Trace for Cyber Investigation: A Meta Learning Approach—0
Self-Supervised Fast Adaptation for Denoising via Meta-Learning—0
Real-Time Edge Intelligence in the Making: A Collaborative Learning Framework via Federated Meta-Learning—0
Frosting Weights for Better Continual TrainingCode0
Dynamic Task Weighting Methods for Multi-task Networks in Autonomous Driving Systems—0
Improving Few-shot Learning by Spatially-aware Matching and CrossTransformer—0
DAWSON: A Domain Adaptive Few Shot Generation Framework—0
Learning Attentive Meta-Transfer—0
Few-shot Relation Extraction via Bayesian Meta-learning on Task Graphs—0
On the Iteration Complexity of Hypergradient Computations—0
Meta Variance Transfer: Learning to Augment from the Others—0
Deep Transfer Learning Based Downlink Channel Prediction for FDD Massive MIMO SystemsCode0
Variational Metric Scaling for Metric-Based Meta-LearningCode0
Meta-Learning PAC-Bayes Priors in Model Averaging—0
Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems with Heterogeneous Sensor Data—0
AutoML: Exploration v.s. ExploitationCode0
Meta-Graph: Few Shot Link Prediction via Meta LearningCode0
TransMatch: A Transfer-Learning Scheme for Semi-Supervised Few-Shot Learning—0
Semantic Regularization: Improve Few-shot Image Classification by Reducing Meta Shift—0
Meta-Learned Per-Instance Algorithm Selection in Scholarly Recommender Systems—0
Continuous Meta-Learning without TasksCode0
Show:102550
← PrevPage 123 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