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 3376–3400 of 3569 papers

TitleStatusHype
ADIOS: Antibody Development via Opponent ShapingCode0
Meta-Learning Probabilistic Inference For PredictionCode0
Arbitrary Scale Super-Resolution for Brain MRI ImagesCode0
A Meta-Learning Method for Estimation of Causal Excursion Effects to Assess Time-Varying ModerationCode0
TaskSet: A Dataset of Optimization TasksCode0
Semi-Modular Inference: enhanced learning in multi-modular models by tempering the influence of componentsCode0
Meta-Learning Representations for Continual LearningCode0
Optimization-Based Deep learning methods for Magnetic Resonance Imaging Reconstruction and SynthesisCode0
Semi-Parametric Inducing Point Networks and Neural ProcessesCode0
A Meta-Learning Framework for Generalized Zero-Shot LearningCode0
Learning to Transfer: Unsupervised Meta Domain TranslationCode0
A Meta-Learning Approach to Bayesian Causal DiscoveryCode0
Meta Learning Shared HierarchiesCode0
Geo-ORBIT: A Federated Digital Twin Framework for Scene-Adaptive Lane Geometry DetectionCode0
Taylorformer: Probabilistic Modelling for Random Processes including Time SeriesCode0
Dataset Distillation using Neural Feature RegressionCode0
Generative vs. Discriminative: Rethinking The Meta-Continual LearningCode0
Meta-learning Spiking Neural Networks with Surrogate Gradient DescentCode0
General-Purpose In-Context Learning by Meta-Learning TransformersCode0
AutoProtoNet: Interpretability for Prototypical NetworksCode0
Using Natural Language and Program Abstractions to Instill Human Inductive Biases in MachinesCode0
Generalizing Supervised Deep Learning MRI Reconstruction to Multiple and Unseen Contrasts using Meta-Learning HypernetworksCode0
TD3: Tucker Decomposition Based Dataset Distillation Method for Sequential RecommendationCode0
Meta-Learning the Difference: Preparing Large Language Models for Efficient AdaptationCode0
Meta-Learning the Inductive Biases of Simple Neural CircuitsCode0
Show:102550
← PrevPage 136 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