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 3201–3225 of 3569 papers

TitleStatusHype
Robust Few-shot Learning Without Using any Adversarial SamplesCode0
Noise-Aware Differentially Private Regression via Meta-LearningCode0
Unsupervised Meta-Learning via Dynamic Head and Heterogeneous Task Construction for Few-Shot ClassificationCode0
Noisy Zero-Shot Coordination: Breaking The Common Knowledge Assumption In Zero-Shot Coordination GamesCode0
Domain Generalization via Semi-supervised Meta LearningCode0
Domain Adaptive Dialog Generation via Meta LearningCode0
Meta-Learning Bidirectional Update RulesCode0
How Low Can We Go: Trading Memory for Error in Low-Precision TrainingCode0
Robust LLM Unlearning with MUDMAN: Meta-Unlearning with Disruption Masking And NormalizationCode0
Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes TheoryCode0
Adaptive Meta-Learning for Robust Deepfake Detection: A Multi-Agent Framework to Data Drift and Model GeneralizationCode0
Does MAML Only Work via Feature Re-use? A Data Centric PerspectiveCode0
Do Ensembling and Meta-Learning Improve Outlier Detection in Randomized Controlled Trials?Code0
Nonsmooth Implicit Differentiation: Deterministic and Stochastic Convergence RatesCode0
Non-stationary Bandits and Meta-Learning with a Small Set of Optimal ArmsCode0
Meta-learning Control Variates: Variance Reduction with Limited DataCode0
Homogeneous Learning: Self-Attention Decentralized Deep LearningCode0
Adaptive Cascading Network for Continual Test-Time AdaptationCode0
Meta Learning Deep Visual Words for Fast Video Object SegmentationCode0
System Prompt Optimization with Meta-LearningCode0
Diversity with Cooperation: Ensemble Methods for Few-Shot ClassificationCode0
T2-Only Prostate Cancer Prediction by Meta-Learning from Bi-Parametric MR ImagingCode0
Robust Meta-learning with Sampling Noise and Label Noise via Eigen-ReptileCode0
High-order structure preserving graph neural network for few-shot learningCode0
META-Learning Eligibility Traces for More Sample Efficient Temporal Difference LearningCode0
Show:102550
← PrevPage 129 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