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 3251–3300 of 3569 papers

TitleStatusHype
Alpha MAML: Adaptive Model-Agnostic Meta-Learning—0
A Meta Understanding of Meta-Learning—0
LEAF: A Benchmark for Federated Settings—0
Enabling Continual Learning in Neural Networks with Meta Learning—0
Deep Knowledge Based Agent: Learning to do tasks by self-thinking about imaginary worlds—0
Meta-Teaching: Curriculum Generation for Lifelong Learning—0
Adaptive Gradient-Based Meta-Learning Methods—0
Learning to learn to communicate—0
Efficient Optimization of Loops and Limits with Randomized Telescoping SumsCode0
TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot LearningCode0
Deep Compressed SensingCode0
Meta Reinforcement Learning with Task Embedding and Shared PolicyCode0
Meta reinforcement learning as task inferenceCode0
Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment—0
Learning What and Where to TransferCode0
LGM-Net: Learning to Generate Matching Networks for Few-Shot LearningCode0
Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems—0
Hierarchically Structured Meta-learningCode0
Few-Shot Viewpoint Estimation—0
Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category GraphCode0
MetaPred: Meta-Learning for Clinical Risk Prediction with Limited Patient Electronic Health RecordsCode0
Data-Efficient Mutual Information Neural Estimator—0
Meta-learning of Sequential Strategies—0
Interpretable Automated Machine Learning in Maana(TM) Knowledge Platform—0
Few-Shot Adaptive Gaze EstimationCode0
Meta-learners' learning dynamics are unlike learners'—0
Attentive Task-Agnostic Meta-Learning for Few-Shot Text Classification—0
Meta-Learning with Domain Adaptation for Few-Shot Learning under Domain Shift—0
Learning to Learn with Conditional Class Dependencies—0
Amortized Bayesian Meta-Learning—0
Transferring SLU Models in Novel Domains—0
Guided Evolutionary Strategies: Escaping the curse of dimensionality in random search—0
Meta-Learning to Guide Segmentation—0
Modulating transfer between tasks in gradient-based meta-learning—0
Sample-efficient policy learning in multi-agent Reinforcement Learning via meta-learning—0
Learning Unsupervised Learning Rules—0
MahiNet: A Neural Network for Many-Class Few-Shot Learning with Class Hierarchy—0
Learning a Meta-Solver for Syntax-Guided Program Synthesis—0
Projective Subspace Networks For Few-Shot Learning—0
Learning from Noisy Demonstration Sets via Meta-Learned Suitability Assessor—0
Learning to Reinforcement Learn by Imitation—0
Learning Meta Model for Zero- and Few-shot Face Anti-spoofing—0
Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID EmbeddingsCode1
META-Learning State-based Eligibility Traces for More Sample-Efficient Policy EvaluationCode0
Hierarchical Meta Learning—0
Meta-Weighted Gaussian Process Experts for Personalized Forecasting of AD Cognitive Changes—0
An Ensemble of Epoch-wise Empirical Bayes for Few-shot LearningCode0
Online Adaptation through Meta-Learning for Stereo Depth Estimation—0
ACE: Adapting to Changing Environments for Semantic Segmentation—0
TAFE-Net: Task-Aware Feature Embeddings for Low Shot LearningCode0
Show:102550
← PrevPage 66 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