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 426450 of 3569 papers

TitleStatusHype
Meta-Learning Dynamics Forecasting Using Task InferenceCode1
Few-Shot Graph Learning for Molecular Property PredictionCode1
A General Descent Aggregation Framework for Gradient-based Bi-level OptimizationCode1
Exploiting Shared Representations for Personalized Federated LearningCode1
Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural networkCode1
Meta Discovery: Learning to Discover Novel Classes given Very Limited DataCode1
Federated Reconstruction: Partially Local Federated LearningCode1
Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agentsCode1
Generalising via Meta-Examples for Continual Learning in the WildCode1
Multilingual and cross-lingual document classification: A meta-learning approachCode1
Efficient Graph Deep Learning in TensorFlow with tf_geometricCode1
Meta Adversarial Training against Universal PatchesCode1
Few-Shot Semantic Parsing for New PredicatesCode1
Nonparametric Estimation of Heterogeneous Treatment Effects: From Theory to Learning AlgorithmsCode1
Few-shot Action Recognition with Prototype-centered Attentive LearningCode1
Few Shot Dialogue State Tracking using Meta-learningCode1
The Gaussian Neural ProcessCode1
Evolving Reinforcement Learning AlgorithmsCode1
Shallow Bayesian Meta Learning for Real-World Few-Shot RecognitionCode1
Few-Shot Learning with Class ImbalanceCode1
Curriculum-Meta Learning for Order-Robust Continual Relation ExtractionCode1
MetaVIM: Meta Variationally Intrinsic Motivated Reinforcement Learning for Decentralized Traffic Signal ControlCode1
Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple ClassifierCode1
IEPT: Instance-Level and Episode-Level Pretext Tasks for Few-Shot LearningCode1
Meta-GMVAE: Mixture of Gaussian VAE for Unsupervised Meta-LearningCode1
Show:102550
← PrevPage 18 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