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 3276–3300 of 3569 papers

TitleStatusHype
Task-Adaptive Meta-Learning Framework for Advancing Spatial GeneralizabilityCode0
Meta-learning based Alternating Minimization Algorithm for Non-convex OptimizationCode0
Artificial Inductive Bias for Synthetic Tabular Data Generation in Data-Scarce ScenariosCode0
Meta-Learning for Natural Language Understanding under Continual Learning FrameworkCode0
Deep Transfer Learning Based Downlink Channel Prediction for FDD Massive MIMO SystemsCode0
Are Structural Concepts Universal in Transformer Language Models? Towards Interpretable Cross-Lingual GeneralizationCode0
Scalable Adversarial Online Continual LearningCode0
Scalable Bayesian Meta-Learning through Generalized Implicit GradientsCode0
Meta-Learning for Online Update of Recommender SystemsCode0
Online Item Cold-Start Recommendation with Popularity-Aware Meta-LearningCode0
Online Learning of a Memory for Learning RatesCode0
Practical Transfer Learning for Bayesian OptimizationCode0
A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded SmoothnessCode0
Deep Task-Based Analog-to-Digital ConversionCode0
Amortised Inference in Bayesian Neural NetworksCode0
Meta-Learning for Resampling Recommendation SystemsCode0
Scalable Online Recurrent Learning Using Columnar Neural NetworksCode0
Scalable Semi-Modular Inference with Variational Meta-PosteriorsCode0
Hacking Task Confounder in Meta-LearningCode0
Guiding Policies with Language via Meta-LearningCode0
Meta-Learning for Simple Regret MinimizationCode0
Adaptive Meta-Learning-Based KKL Observer Design for Nonlinear Dynamical SystemsCode0
Two-stage Optimization for Machine Learning WorkflowCode0
Meta-Learning for Stochastic Gradient MCMCCode0
Meta-Learning for Symbolic Hyperparameter DefaultsCode0
Show:102550
← PrevPage 132 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