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 651–700 of 3569 papers

TitleStatusHype
A Simple Approach to Case-Based Reasoning in Knowledge BasesCode1
Induction Networks for Few-Shot Text ClassificationCode1
Cross-Domain Few-Shot Classification via Adversarial Task AugmentationCode1
Speeding Up Multi-Objective Hyperparameter Optimization by Task Similarity-Based Meta-Learning for the Tree-Structured Parzen EstimatorCode1
From Learning to Meta-Learning: Reduced Training Overhead and Complexity for Communication SystemsCode1
Inductive-Associative Meta-learning Pipeline with Human Cognitive Patterns for Unseen Drug-Target Interaction PredictionCode0
A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded SmoothnessCode0
Two Sides of Meta-Learning Evaluation: In vs. Out of DistributionCode0
Adversarial Meta-Learning of Gamma-Minimax Estimators That Leverage Prior KnowledgeCode0
A Cost-Sensitive Meta-Learning Strategy for Fair Provider Exposure in RecommendationCode0
LeMON: Learning to Learn Multi-Operator NetworksCode0
LGM-Net: Learning to Generate Matching Networks for Few-Shot LearningCode0
Learning vs Retrieval: The Role of In-Context Examples in Regression with LLMsCode0
B-SMALL: A Bayesian Neural Network approach to Sparse Model-Agnostic Meta-LearningCode0
Learning What and Where to TransferCode0
Learning Unknowns from Unknowns: Diversified Negative Prototypes Generator for Few-Shot Open-Set RecognitionCode0
Meta-learning Convolutional Neural Architectures for Multi-target Concrete Defect Classification with the COncrete DEfect BRidge IMage DatasetCode0
Learning Where to Edit Vision TransformersCode0
L-HYDRA: Multi-Head Physics-Informed Neural NetworksCode0
Learning to Rasterize DifferentiablyCode0
Learning to Rectify for Robust Learning with Noisy LabelsCode0
Bottom-Up Meta-Policy SearchCode0
Bootstrapping Informative Graph Augmentation via A Meta Learning ApproachCode0
Learning to reinforcement learnCode0
Bootstrapped Meta-LearningCode0
Learning to Propagate Labels: Transductive Propagation Network for Few-shot LearningCode0
Learning to Multi-Task by Active SamplingCode0
Learning to Propagate for Graph Meta-LearningCode0
Learning to reinforcement learn for Neural Architecture SearchCode0
Boosting Lightweight Single Image Super-resolution via Joint-distillationCode0
Learning to Learn Transferable AttackCode0
Amortised Inference in Bayesian Neural NetworksCode0
Learning to Learn Variational Semantic MemoryCode0
Learning to Learn Words from Visual ScenesCode0
Learning to Learn Single Domain GeneralizationCode0
Bayesian Active Meta-Learning for Few Pilot Demodulation and EqualizationCode0
A Bridge Between Hyperparameter Optimization and Learning-to-learnCode0
Learning to Learn Kernels with Variational Random FeaturesCode0
Learning to Modulate Random Weights: Neuromodulation-inspired Neural Networks For Efficient Continual LearningCode0
LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing PlatformsCode0
Learning to Learn Cropping Models for Different Aspect Ratio RequirementsCode0
Blinder: End-to-end Privacy Protection in Sensing Systems via Personalized Federated LearningCode0
Learning to Learn By Self-CritiqueCode0
Learning to learn ecosystems from limited data -- a meta-learning approachCode0
A MIND for Reasoning: Meta-learning for In-context DeductionCode0
Black box meta-learning intrinsic rewards for sparse-reward environmentsCode0
Learning to Generate Noise for Multi-Attack RobustnessCode0
Learning to learn by gradient descent by gradient descentCode0
BioAct-Het: A Heterogeneous Siamese Neural Network for Bioactivity Prediction Using Novel Bioactivity RepresentatioCode0
A Meta-Transfer Objective for Learning to Disentangle Causal MechanismsCode0
Show:102550
← PrevPage 14 of 72Next →
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