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 1301–1325 of 3569 papers

TitleStatusHype
Graph Neural Network Expressivity and Meta-Learning for Molecular Property Regression—0
Graph neural network initialisation of quantum approximate optimisation—0
Generative Neural Fields by Mixtures of Neural Implicit Functions—0
Generative Meta-Learning for Zero-Shot Relation Triplet Extraction—0
Generative Conversational Networks—0
A Review on Semi-Supervised Relation Extraction—0
Generating Pseudo-labels Adaptively for Few-shot Model-Agnostic Meta-Learning—0
Generating Personalized Dialogue via Multi-Task Meta-Learning—0
Group Equivariant Conditional Neural Processes—0
Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning—0
Cross-Domain Few-Shot Learning with Meta Fine-Tuning—0
Generating meta-learning tasks to evolve parametric loss for classification learning—0
A Heuristic Search Algorithm Using the Stability of Learning Algorithms in Certain Scenarios as the Fitness Function: An Artificial General Intelligence Engineering Approach—0
Guided Evolutionary Strategies: Escaping the curse of dimensionality in random search—0
A Review of Meta-level Learning in the Context of Multi-component, Multi-level Evolving Prediction Systems—0
Guided Variational Autoencoder for Disentanglement Learning—0
A Generalized Alternating Method for Bilevel Learning under the Polyak-Łojasiewicz Condition—0
A Simple Recipe to Meta-Learn Forward and Backward Transfer—0
Inductive Linear Probing for Few-shot Node Classification—0
Inexact-ADMM Based Federated Meta-Learning for Fast and Continual Edge Learning—0
Accelerating Online Reinforcement Learning via Model-Based Meta-Learning—0
Generalized Zero-Shot Learning using Multimodal Variational Auto-Encoder with Semantic Concepts—0
Bayesian Inverse Physics for Neuro-Symbolic Robot Learning—0
Heterosynaptic Circuits Are Universal Gradient Machines—0
Inferential Text Generation with Multiple Knowledge Sources and Meta-Learning—0
Show:102550
← PrevPage 53 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