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 3001–3025 of 3569 papers

TitleStatusHype
HetMAML: Task-Heterogeneous Model-Agnostic Meta-Learning for Few-Shot Learning Across Modalities—0
Hidden Incentives for Auto-Induced Distributional Shift—0
Hidden incentives for self-induced distributional shift—0
Hierarchical end-to-end autonomous navigation through few-shot waypoint detection—0
Hierarchical Expert Networks for Meta-Learning—0
Hierarchical Meta Learning—0
Higher-Order Generalization Bounds: Learning Deep Probabilistic Programs via PAC-Bayes Objectives—0
High-Order Deep Meta-Learning with Category-Theoretic Interpretation—0
Home Appliance Review Research Via Adversarial Reptile—0
Homomorphisms Between Transfer, Multi-Task, and Meta-Learning Systems—0
How Fine-Tuning Allows for Effective Meta-Learning—0
How Important is the Train-Validation Split in Meta-Learning?—0
How Much Is Hidden in the NAS Benchmarks? Few-Shot Adaptation of a NAS Predictor—0
How to distribute data across tasks for meta-learning?—0
How well does your sampler really work?—0
HUB: Guiding Learned Optimizers with Continuous Prompt Tuning—0
Hybrid Consistency Training with Prototype Adaptation for Few-Shot Learning—0
Hybrid Control Policy for Artificial Pancreas via Ensemble Deep Reinforcement Learning—0
Hybrid Meta-Learning Framework for Anomaly Forecasting in Nonlinear Dynamical Systems via Physics-Inspired Simulation and Deep Ensembles—0
Hybrid Multi-stage Decoding for Few-shot NER with Entity-aware Contrastive Learning—0
Hybrid-Task Meta-Learning: A Graph Neural Network Approach for Scalable and Transferable Bandwidth Allocation—0
Hyperbolic Dual Feature Augmentation for Open-Environment—0
Hyperbolic Graph Neural Networks at Scale: A Meta Learning Approach—0
HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworks—0
HyPer-EP: Meta-Learning Hybrid Personalized Models for Cardiac Electrophysiology—0
Show:102550
← PrevPage 121 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