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 701–710 of 3569 papers

TitleStatusHype
Boosting Black-Box Adversarial Attacks with Meta Learning—0
A model-based approach to meta-Reinforcement Learning: Transformers and tree search—0
Adaptive Self-training for Few-shot Neural Sequence Labeling—0
Efficient Continual Adaptation of Pretrained Robotic Policy with Online Meta-Learned Adapters—0
Efficient Gaussian Neural Processes for Regression—0
Efficient Meta-Learning Enabled Lightweight Multiscale Few-Shot Object Detection in Remote Sensing Images—0
A Model-based Approach for Sample-efficient Multi-task Reinforcement Learning—0
AMM: Adaptive Modularized Reinforcement Model for Multi-city Traffic Signal Control—0
Automatic Self-supervised Learning for Social Recommendations—0
Efficient Quantum State Sample Tomography with Basis-dependent Neural-networks—0
Show:102550
← PrevPage 71 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