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 771–780 of 3569 papers

TitleStatusHype
Hyperbolic Graph Neural Networks at Scale: A Meta Learning Approach—0
Episodic Multi-Task Learning with Heterogeneous Neural ProcessesCode0
On Training Implicit Meta-Learning With Applications to Inductive Weighing in Consistency Regularization—0
Contextual Stochastic Bilevel Optimization—0
CosmosDSR -- a methodology for automated detection and tracking of orbital debris using the Unscented Kalman Filter—0
RedCoast: A Lightweight Tool to Automate Distributed Training of LLMs on Any GPU/TPUsCode1
Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-EncoderCode1
Amortised Inference in Neural Networks for Small-Scale Probabilistic Meta-Learning—0
Knowledge-driven Meta-learning for CSI Feedback—0
Deceptive Fairness Attacks on Graphs via Meta LearningCode0
Show:102550
← PrevPage 78 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