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 2811–2820 of 3569 papers

TitleStatusHype
Unfairness Discovery and Prevention For Few-Shot Regression—0
Fair Meta-Learning For Few-Shot Classification—0
Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time—0
Feed-Forward On-Edge Fine-tuning Using Static Synthetic Gradient Modules—0
Adaptive Meta-Learning for Identification of Rover-Terrain DynamicsCode0
Learning Soft Labels via Meta Learning—0
Hidden Incentives for Auto-Induced Distributional Shift—0
GeneraLight: Improving Environment Generalization of Traffic Signal Control via Meta Reinforcement Learning—0
An Extensive Experimental Evaluation of Automated Machine Learning Methods for Recommending Classification Algorithms (Extended Version)—0
Efficient Quantum State Sample Tomography with Basis-dependent Neural-networks—0
Show:102550
← PrevPage 282 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