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

Showing 901925 of 3569 papers

TitleStatusHype
Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text GenerationCode0
Learning Invariances for Policy GeneralizationCode0
Learning New Tasks from a Few Examples with Soft-Label PrototypesCode0
Learning Task-Aware Energy Disaggregation: a Federated ApproachCode0
Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal PredictionCode0
Efficient Optimization of Loops and Limits with Randomized Telescoping SumsCode0
Adaptive Prior Selection for Repertoire-based Online Adaptation in RoboticsCode0
Efficient time stepping for numerical integration using reinforcement learningCode0
Learning Fast Adaptation with Meta Strategy OptimizationCode0
Meta-learning from Tasks with Heterogeneous Attribute SpacesCode0
Capability-Aware Shared Hypernetworks for Flexible Heterogeneous Multi-Robot CoordinationCode0
Meta-Learning Integration in Hierarchical Reinforcement Learning for Advanced Task ComplexityCode0
Meta-Learning of Structured Task Distributions in Humans and MachinesCode0
Learning Generalized Zero-Shot Learners for Open-Domain Image GeolocalizationCode0
Attentional Meta-learners for Few-shot Polythetic ClassificationCode0
Learning Deep Morphological Networks with Neural Architecture SearchCode0
Zero-shot task adaptation by homoiconic meta-mappingCode0
Meta-Learning on Augmented Gene Expression Profiles for Enhanced Lung Cancer DetectionCode0
Image Deformation Meta-Networks for One-Shot LearningCode0
Learning an Explicit Hyperparameter Prediction Function Conditioned on TasksCode0
Learning to acquire novel cognitive tasks with evolution, plasticity and meta-meta-learningCode0
Meta Learning Shared HierarchiesCode0
Deep Learning Theory Review: An Optimal Control and Dynamical Systems PerspectiveCode0
learn2learn: A Library for Meta-Learning ResearchCode0
An Ensemble of Epoch-wise Empirical Bayes for Few-shot LearningCode0
Show:102550
← PrevPage 37 of 143Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-train success rate97.8Unverified
2MZMeta-train success rate97.6Unverified
3MAMLMeta-test success rate36Unverified
4RL^2Meta-test success rate10Unverified
5DnCMeta-test success rate5.4Unverified
6PEARLMeta-test success rate0Unverified
#ModelMetricClaimedVerifiedStatus
1SoftModuleAverage Success Rate60Unverified
2Multi-task multi-head SACAverage Success Rate35.85Unverified
3DisCorAverage Success Rate26Unverified
4NDPAverage Success Rate11Unverified
#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-test success rate (zero-shot)18.5Unverified
2MZMeta-test success rate (zero-shot)17.7Unverified
#ModelMetricClaimedVerifiedStatus
1Metadrop% Test Accuracy95.75Unverified