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 951–1000 of 3569 papers

TitleStatusHype
Virtual Node Tuning for Few-shot Node Classification—0
EMO: Episodic Memory Optimization for Few-Shot Meta-Learning—0
In-Context Learning through the Bayesian PrismCode0
Meta-Learning in Spiking Neural Networks with Reward-Modulated STDP—0
Decentralized Multi-Level Compositional Optimization Algorithms with Level-Independent Convergence Rate—0
GSHOT: Few-shot Generative Modeling of Labeled GraphsCode0
Meta-SAGE: Scale Meta-Learning Scheduled Adaptation with Guided Exploration for Mitigating Scale Shift on Combinatorial OptimizationCode1
Evolution of Efficient Symbolic Communication Codes—0
Multi-Predict: Few Shot Predictors For Efficient Neural Architecture Search—0
A Generalized Alternating Method for Bilevel Learning under the Polyak-Łojasiewicz Condition—0
TART: Improved Few-shot Text Classification Using Task-Adaptive Reference TransformationCode0
Meta-Learning Framework for End-to-End Imposter Identification in Unseen Speaker Recognition—0
Effective Structured Prompting by Meta-Learning and Representative VerbalizerCode0
MetaXLR -- Mixed Language Meta Representation Transformation for Low-resource Cross-lingual Learning based on Multi-Armed BanditCode0
Towards Omni-generalizable Neural Methods for Vehicle Routing ProblemsCode1
SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learning—0
Adaptive Conditional Quantile Neural ProcessesCode0
Taylorformer: Probabilistic Modelling for Random Processes including Time SeriesCode0
AlteredAvatar: Stylizing Dynamic 3D Avatars with Fast Style Adaptation—0
Task-Equivariant Graph Few-shot LearningCode1
Joint Optimization of Class-Specific Training- and Test-Time Data Augmentation in SegmentationCode0
A Meta-learning Framework for Tuning Parameters of Protection Mechanisms in Trustworthy Federated Learning—0
Learning to Learn from APIs: Black-Box Data-Free Meta-LearningCode1
Zero- and Few-Shot Event Detection via Prompt-Based Meta LearningCode1
Im-Promptu: In-Context Composition from Image PromptsCode0
HUB: Guiding Learned Optimizers with Continuous Prompt Tuning—0
Meta-prediction Model for Distillation-Aware NAS on Unseen DatasetsCode1
Meta-learning For Vision-and-language Cross-lingual Transfer—0
Test like you Train in Implicit Deep Learning—0
Meta-Learning Online Adaptation of Language ModelsCode1
MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic SegmentationCode1
Memory Efficient Neural Processes via Constant Memory Attention BlockCode0
Clustering Indices based Automatic Classification Model SelectionCode0
Improving Convergence and Generalization Using Parameter SymmetriesCode1
A Meta-learning based Generalizable Indoor Localization Model using Channel State Information—0
Effective Bilevel Optimization via Minimax Reformulation—0
Improved Compositional Generalization by Generating Demonstrations for Meta-Learning—0
Mitigating Catastrophic Forgetting for Few-Shot Spoken Word Classification Through Meta-LearningCode0
MetaAdapt: Domain Adaptive Few-Shot Misinformation Detection via Meta LearningCode1
Single Domain Dynamic Generalization for Iris Presentation Attack Detection—0
Many or Few Samples? Comparing Transfer, Contrastive and Meta-Learning in Encrypted Traffic Classification—0
Self-Distillation with Meta Learning for Knowledge Graph CompletionCode0
Meta Neural Coordination—0
ALT: An Automatic System for Long Tail Scenario Modeling—0
Meta-learning for heterogeneous treatment effect estimation with closed-form solvers—0
MetaGAD: Meta Representation Adaptation for Few-Shot Graph Anomaly DetectionCode0
Meta-Auxiliary Network for 3D GAN Inversion—0
MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer TasksCode1
RAMario: Experimental Approach to Reptile Algorithm -- Reinforcement Learning for MarioCode0
Automatic learning algorithm selection for classification via convolutional neural networks—0
Show:102550
← PrevPage 20 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