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 1201–1225 of 3569 papers

TitleStatusHype
Improving Generalization via Meta-Learning on Hard Samples—0
Compositional learning of functions in humans and machines—0
Nonsmooth Implicit Differentiation: Deterministic and Stochastic Convergence RatesCode0
HyPer-EP: Meta-Learning Hybrid Personalized Models for Cardiac Electrophysiology—0
Meta Operator for Complex Query Answering on Knowledge Graphs—0
AutoLoRA: Automatically Tuning Matrix Ranks in Low-Rank Adaptation Based on Meta Learning—0
Search-based Optimisation of LLM Learning Shots for Story Point Estimation—0
Unsupervised Learning of Hybrid Latent Dynamics: A Learn-to-Identify Framework—0
Distributed Estimation by Two Agents with Different Feature Spaces—0
All in One: Multi-Task Prompting for Graph Neural Networks (Extended Abstract)—0
XB-MAML: Learning Expandable Basis Parameters for Effective Meta-Learning with Wide Task CoverageCode0
MetaSplit: Meta-Split Network for Limited-Stock Product Recommendation—0
Provable Multi-Party Reinforcement Learning with Diverse Human Feedback—0
Rethinking of Encoder-based Warm-start Methods in Hyperparameter OptimizationCode0
Boosting Meta-Training with Base Class Information for Few-Shot Learning—0
Learning to Defer to a Population: A Meta-Learning ApproachCode0
Decomposed Meta-Learning for Few-Shot Sequence LabelingCode0
Transformers for Supervised Online Continual Learning—0
CCML: Curriculum and Contrastive Learning Enhanced Meta-Learner for Personalized Spatial Trajectory Prediction—0
BP-DeepONet: A new method for cuffless blood pressure estimation using the physcis-informed DeepONet—0
Parallel Momentum Methods Under Biased Gradient Estimations—0
FORML: A Riemannian Hessian-free Method for Meta-learning on Stiefel Manifolds—0
Meta-Tasks: An alternative view on Meta-Learning Regularization—0
Single Neuromorphic Memristor closely Emulates Multiple Synaptic Mechanisms for Energy Efficient Neural Networks—0
Few-Shot Learning for Annotation-Efficient Nucleus Instance Segmentation—0
Show:102550
← PrevPage 49 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