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 3311–3320 of 3569 papers

TitleStatusHype
Meta-learning from Tasks with Heterogeneous Attribute SpacesCode0
Unsupervised Task Clustering for Multi-Task Reinforcement LearningCode0
Deep Learning Theory Review: An Optimal Control and Dynamical Systems PerspectiveCode0
A MIND for Reasoning: Meta-learning for In-context DeductionCode0
Task Augmentation by Rotating for Meta-LearningCode0
Meta-learning how to Share Credit among Macro-ActionsCode0
Deep Compressed SensingCode0
SeFNet: Bridging Tabular Datasets with Semantic Feature NetsCode0
Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text GenerationCode0
Decomposed Meta-Learning for Few-Shot Sequence LabelingCode0
Show:102550
← PrevPage 332 of 357Next →
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