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 3151–3175 of 3569 papers

TitleStatusHype
Learning Efficient and Effective Exploration Policies with Counterfactual Meta Policy—0
Learning Fast Sample Re-weighting Without Reward Data—0
Learning Feature Relevance Through Step Size Adaptation in Temporal-Difference Learning—0
Reconstruction guided Meta-learning for Few Shot Open Set Recognition—0
Learning from Few Examples: A Summary of Approaches to Few-Shot Learning—0
Learning from Few Samples: A Survey—0
Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks—0
Learning from Noisy Demonstration Sets via Meta-Learned Suitability Assessor—0
Learning from Noisy Labels via Self-Taught On-the-Fly Meta Loss Rescaling—0
Learning from the Past: Continual Meta-Learning via Bayesian Graph Modeling—0
A Survey on Machine Learning from Few Samples—0
Learning Functional Priors and Posteriors from Data and Physics—0
Learning Generative Prior with Latent Space Sparsity Constraints—0
Learning Intrinsic and Extrinsic Intentions for Cold-start Recommendation with Neural Stochastic Processes—0
Learning Knowledge Representation with Meta Knowledge Distillation for Single Image Super-Resolution—0
Learning Low-dimensional Latent Dynamics from High-dimensional Observations: Non-asymptotics and Lower Bounds—0
Learning Low-Resource End-To-End Goal-Oriented Dialog for Fast and Reliable System Deployment—0
Learning Modality Knowledge Alignment for Cross-Modality Transfer—0
Learning Neural Processes on the Fly—0
Learning Not to Learn: Nature versus Nurture in Silico—0
Learning Online for Unified Segmentation and Tracking Models—0
Instance-Conditional Timescales of Decay for Non-Stationary Learning—0
Learning Prototype-oriented Set Representations for Meta-Learning—0
Learning Soft Labels via Meta Learning—0
Learning State-Dependent Losses for Inverse Dynamics Learning—0
Show:102550
← PrevPage 127 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