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 1476–1500 of 3569 papers

TitleStatusHype
Customized Conversational Recommender Systems—0
Meta-Learning over Time for Destination Prediction Tasks—0
Dual Attention Networks for Few-Shot Fine-Grained RecognitionCode0
Meta-Wrapper: Differentiable Wrapping Operator for User Interest Selection in CTR Prediction—0
Leveraging Language for Accelerated Learning of Tool Manipulation—0
Understanding Benign Overfitting in Gradient-Based Meta Learning—0
p-Meta: Towards On-device Deep Model Adaptation—0
On the Generalizability and Predictability of Recommender SystemsCode1
Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks—0
Multi-Access Point Coordination for Next-Gen Wi-Fi Networks Aided by Deep Reinforcement Learning—0
Meta-learning for Out-of-Distribution Detection via Density Estimation in Latent Space—0
MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot SegmentationCode1
MetaGL: Evaluation-Free Selection of Graph Learning Models via Meta-LearningCode0
Provable Generalization of Overparameterized Meta-learning Trained with SGD—0
EEML: Ensemble Embedded Meta-learning—0
Motley: Benchmarking Heterogeneity and Personalization in Federated LearningCode0
Principled Acceleration of Iterative Numerical Methods Using Machine Learning—0
FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image ClassificationCode1
Fast Finite Width Neural Tangent KernelCode0
Zero-Shot AutoML with Pretrained ModelsCode1
On Enforcing Better Conditioned Meta-Learning for Rapid Few-Shot Adaptation—0
RecBole 2.0: Towards a More Up-to-Date Recommendation LibraryCode4
Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification—0
Category-Agnostic 6D Pose Estimation with Conditional Neural Processes—0
On Provably Robust Meta-Bayesian OptimizationCode0
Show:102550
← PrevPage 60 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